agentdb 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +38 -0
- package/LICENSE-APACHE +190 -0
- package/LICENSE-MIT +21 -0
- package/README.md +953 -0
- package/bin/agentdb.js +485 -0
- package/bin/plugin-cli-wrapper.mjs +21 -0
- package/dist/cache/query-cache.d.ts +105 -0
- package/dist/cache/query-cache.d.ts.map +1 -0
- package/dist/cache/query-cache.js +224 -0
- package/dist/cache/query-cache.js.map +1 -0
- package/dist/cache/query-cache.mjs +219 -0
- package/dist/cli/cache/query-cache.d.ts +104 -0
- package/dist/cli/cache/query-cache.js +244 -0
- package/dist/cli/cli/db-commands.d.ts +48 -0
- package/dist/cli/cli/db-commands.js +613 -0
- package/dist/cli/commands.d.ts +7 -0
- package/dist/cli/commands.d.ts.map +1 -0
- package/dist/cli/commands.js +113 -0
- package/dist/cli/commands.js.map +1 -0
- package/dist/cli/commands.mjs +104 -0
- package/dist/cli/core/backend-interface.d.ts +70 -0
- package/dist/cli/core/backend-interface.js +15 -0
- package/dist/cli/core/native-backend.d.ts +140 -0
- package/dist/cli/core/native-backend.js +432 -0
- package/dist/cli/core/vector-db.d.ts +126 -0
- package/dist/cli/core/vector-db.js +338 -0
- package/dist/cli/core/wasm-backend.d.ts +95 -0
- package/dist/cli/core/wasm-backend.js +418 -0
- package/dist/cli/db-commands.d.ts +49 -0
- package/dist/cli/db-commands.d.ts.map +1 -0
- package/dist/cli/db-commands.js +533 -0
- package/dist/cli/db-commands.js.map +1 -0
- package/dist/cli/db-commands.mjs +522 -0
- package/dist/cli/generator.d.ts +11 -0
- package/dist/cli/generator.d.ts.map +1 -0
- package/dist/cli/generator.js +567 -0
- package/dist/cli/generator.js.map +1 -0
- package/dist/cli/generator.mjs +527 -0
- package/dist/cli/help.d.ts +18 -0
- package/dist/cli/help.d.ts.map +1 -0
- package/dist/cli/help.js +676 -0
- package/dist/cli/help.js.map +1 -0
- package/dist/cli/help.mjs +667 -0
- package/dist/cli/index/hnsw.d.ts +164 -0
- package/dist/cli/index/hnsw.js +558 -0
- package/dist/cli/plugin-cli.d.ts +7 -0
- package/dist/cli/plugin-cli.d.ts.map +1 -0
- package/dist/cli/plugin-cli.js +295 -0
- package/dist/cli/plugin-cli.js.map +1 -0
- package/dist/cli/plugin-cli.mjs +289 -0
- package/dist/cli/quantization/product-quantization.d.ts +108 -0
- package/dist/cli/quantization/product-quantization.js +350 -0
- package/dist/cli/query/query-builder.d.ts +322 -0
- package/dist/cli/query/query-builder.js +600 -0
- package/dist/cli/templates.d.ts +14 -0
- package/dist/cli/templates.d.ts.map +1 -0
- package/dist/cli/templates.js +182 -0
- package/dist/cli/templates.js.map +1 -0
- package/dist/cli/templates.mjs +176 -0
- package/dist/cli/types/index.d.ts +116 -0
- package/dist/cli/types/index.js +5 -0
- package/dist/cli/types.d.ts +91 -0
- package/dist/cli/types.d.ts.map +1 -0
- package/dist/cli/types.js +6 -0
- package/dist/cli/types.js.map +1 -0
- package/dist/cli/types.mjs +4 -0
- package/dist/cli/wizard/index.d.ts +6 -0
- package/dist/cli/wizard/index.d.ts.map +1 -0
- package/dist/cli/wizard/index.js +138 -0
- package/dist/cli/wizard/index.js.map +1 -0
- package/dist/cli/wizard/index.mjs +131 -0
- package/dist/cli/wizard/prompts.d.ts +11 -0
- package/dist/cli/wizard/prompts.d.ts.map +1 -0
- package/dist/cli/wizard/prompts.js +482 -0
- package/dist/cli/wizard/prompts.js.map +1 -0
- package/dist/cli/wizard/prompts.mjs +470 -0
- package/dist/cli/wizard/validator.d.ts +13 -0
- package/dist/cli/wizard/validator.d.ts.map +1 -0
- package/dist/cli/wizard/validator.js +234 -0
- package/dist/cli/wizard/validator.js.map +1 -0
- package/dist/cli/wizard/validator.mjs +224 -0
- package/dist/core/backend-interface.d.ts +71 -0
- package/dist/core/backend-interface.d.ts.map +1 -0
- package/dist/core/backend-interface.js +16 -0
- package/dist/core/backend-interface.js.map +1 -0
- package/dist/core/backend-interface.mjs +12 -0
- package/dist/core/native-backend.d.ts +141 -0
- package/dist/core/native-backend.d.ts.map +1 -0
- package/dist/core/native-backend.js +457 -0
- package/dist/core/native-backend.js.map +1 -0
- package/dist/core/native-backend.mjs +449 -0
- package/dist/core/vector-db.d.ts +127 -0
- package/dist/core/vector-db.d.ts.map +1 -0
- package/dist/core/vector-db.js +266 -0
- package/dist/core/vector-db.js.map +1 -0
- package/dist/core/vector-db.mjs +261 -0
- package/dist/core/wasm-backend.d.ts +96 -0
- package/dist/core/wasm-backend.d.ts.map +1 -0
- package/dist/core/wasm-backend.js +393 -0
- package/dist/core/wasm-backend.js.map +1 -0
- package/dist/core/wasm-backend.mjs +385 -0
- package/dist/index/hnsw-optimized.d.ts +75 -0
- package/dist/index/hnsw-optimized.d.ts.map +1 -0
- package/dist/index/hnsw-optimized.js +412 -0
- package/dist/index/hnsw-optimized.js.map +1 -0
- package/dist/index/hnsw-optimized.mjs +407 -0
- package/dist/index/hnsw.d.ts +165 -0
- package/dist/index/hnsw.d.ts.map +1 -0
- package/dist/index/hnsw.js +521 -0
- package/dist/index/hnsw.js.map +1 -0
- package/dist/index/hnsw.mjs +516 -0
- package/dist/index.d.ts +57 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +82 -0
- package/dist/index.js.map +1 -0
- package/dist/index.mjs +63 -0
- package/dist/mcp-server.d.ts +27 -0
- package/dist/mcp-server.d.ts.map +1 -0
- package/dist/mcp-server.js +789 -0
- package/dist/mcp-server.js.map +1 -0
- package/dist/mcp-server.mjs +784 -0
- package/dist/plugins/base-plugin.d.ts +114 -0
- package/dist/plugins/base-plugin.d.ts.map +1 -0
- package/dist/plugins/base-plugin.js +313 -0
- package/dist/plugins/base-plugin.js.map +1 -0
- package/dist/plugins/base-plugin.mjs +275 -0
- package/dist/plugins/implementations/active-learning.d.ts +135 -0
- package/dist/plugins/implementations/active-learning.d.ts.map +1 -0
- package/dist/plugins/implementations/active-learning.js +372 -0
- package/dist/plugins/implementations/active-learning.js.map +1 -0
- package/dist/plugins/implementations/active-learning.mjs +367 -0
- package/dist/plugins/implementations/actor-critic.d.ts +64 -0
- package/dist/plugins/implementations/actor-critic.d.ts.map +1 -0
- package/dist/plugins/implementations/actor-critic.js +363 -0
- package/dist/plugins/implementations/actor-critic.js.map +1 -0
- package/dist/plugins/implementations/actor-critic.mjs +358 -0
- package/dist/plugins/implementations/adversarial-training.d.ts +133 -0
- package/dist/plugins/implementations/adversarial-training.d.ts.map +1 -0
- package/dist/plugins/implementations/adversarial-training.js +409 -0
- package/dist/plugins/implementations/adversarial-training.js.map +1 -0
- package/dist/plugins/implementations/adversarial-training.mjs +404 -0
- package/dist/plugins/implementations/curriculum-learning.d.ts +132 -0
- package/dist/plugins/implementations/curriculum-learning.d.ts.map +1 -0
- package/dist/plugins/implementations/curriculum-learning.js +354 -0
- package/dist/plugins/implementations/curriculum-learning.js.map +1 -0
- package/dist/plugins/implementations/curriculum-learning.mjs +349 -0
- package/dist/plugins/implementations/decision-transformer.d.ts +77 -0
- package/dist/plugins/implementations/decision-transformer.d.ts.map +1 -0
- package/dist/plugins/implementations/decision-transformer.js +422 -0
- package/dist/plugins/implementations/decision-transformer.js.map +1 -0
- package/dist/plugins/implementations/decision-transformer.mjs +417 -0
- package/dist/plugins/implementations/federated-learning.d.ts +126 -0
- package/dist/plugins/implementations/federated-learning.d.ts.map +1 -0
- package/dist/plugins/implementations/federated-learning.js +436 -0
- package/dist/plugins/implementations/federated-learning.js.map +1 -0
- package/dist/plugins/implementations/federated-learning.mjs +431 -0
- package/dist/plugins/implementations/index.d.ts +30 -0
- package/dist/plugins/implementations/index.d.ts.map +1 -0
- package/dist/plugins/implementations/index.js +45 -0
- package/dist/plugins/implementations/index.js.map +1 -0
- package/dist/plugins/implementations/index.mjs +31 -0
- package/dist/plugins/implementations/multi-task-learning.d.ts +115 -0
- package/dist/plugins/implementations/multi-task-learning.d.ts.map +1 -0
- package/dist/plugins/implementations/multi-task-learning.js +369 -0
- package/dist/plugins/implementations/multi-task-learning.js.map +1 -0
- package/dist/plugins/implementations/multi-task-learning.mjs +364 -0
- package/dist/plugins/implementations/neural-architecture-search.d.ts +148 -0
- package/dist/plugins/implementations/neural-architecture-search.d.ts.map +1 -0
- package/dist/plugins/implementations/neural-architecture-search.js +379 -0
- package/dist/plugins/implementations/neural-architecture-search.js.map +1 -0
- package/dist/plugins/implementations/neural-architecture-search.mjs +374 -0
- package/dist/plugins/implementations/q-learning.d.ts +98 -0
- package/dist/plugins/implementations/q-learning.d.ts.map +1 -0
- package/dist/plugins/implementations/q-learning.js +435 -0
- package/dist/plugins/implementations/q-learning.js.map +1 -0
- package/dist/plugins/implementations/q-learning.mjs +430 -0
- package/dist/plugins/implementations/sarsa.d.ts +103 -0
- package/dist/plugins/implementations/sarsa.d.ts.map +1 -0
- package/dist/plugins/implementations/sarsa.js +347 -0
- package/dist/plugins/implementations/sarsa.js.map +1 -0
- package/dist/plugins/implementations/sarsa.mjs +342 -0
- package/dist/plugins/index.d.ts +107 -0
- package/dist/plugins/index.d.ts.map +1 -0
- package/dist/plugins/index.js +179 -0
- package/dist/plugins/index.js.map +1 -0
- package/dist/plugins/index.mjs +168 -0
- package/dist/plugins/interface.d.ts +439 -0
- package/dist/plugins/interface.d.ts.map +1 -0
- package/dist/plugins/interface.js +12 -0
- package/dist/plugins/interface.js.map +1 -0
- package/dist/plugins/interface.mjs +10 -0
- package/dist/plugins/learning-plugin.interface.d.ts +257 -0
- package/dist/plugins/learning-plugin.interface.d.ts.map +1 -0
- package/dist/plugins/learning-plugin.interface.js +7 -0
- package/dist/plugins/learning-plugin.interface.js.map +1 -0
- package/dist/plugins/learning-plugin.interface.mjs +5 -0
- package/dist/plugins/plugin-exports.d.ts +71 -0
- package/dist/plugins/plugin-exports.d.ts.map +1 -0
- package/dist/plugins/plugin-exports.js +78 -0
- package/dist/plugins/plugin-exports.js.map +1 -0
- package/dist/plugins/plugin-exports.mjs +69 -0
- package/dist/plugins/registry.d.ts +206 -0
- package/dist/plugins/registry.d.ts.map +1 -0
- package/dist/plugins/registry.js +365 -0
- package/dist/plugins/registry.js.map +1 -0
- package/dist/plugins/registry.mjs +356 -0
- package/dist/plugins/validator.d.ts +63 -0
- package/dist/plugins/validator.d.ts.map +1 -0
- package/dist/plugins/validator.js +464 -0
- package/dist/plugins/validator.js.map +1 -0
- package/dist/plugins/validator.mjs +458 -0
- package/dist/quantization/binary-quantization.d.ts +104 -0
- package/dist/quantization/binary-quantization.d.ts.map +1 -0
- package/dist/quantization/binary-quantization.js +246 -0
- package/dist/quantization/binary-quantization.js.map +1 -0
- package/dist/quantization/binary-quantization.mjs +240 -0
- package/dist/quantization/optimized-pq.d.ts +138 -0
- package/dist/quantization/optimized-pq.d.ts.map +1 -0
- package/dist/quantization/optimized-pq.js +320 -0
- package/dist/quantization/optimized-pq.js.map +1 -0
- package/dist/quantization/optimized-pq.mjs +313 -0
- package/dist/quantization/product-quantization.d.ts +109 -0
- package/dist/quantization/product-quantization.d.ts.map +1 -0
- package/dist/quantization/product-quantization.js +287 -0
- package/dist/quantization/product-quantization.js.map +1 -0
- package/dist/quantization/product-quantization.mjs +282 -0
- package/dist/quantization/scalar-quantization.d.ts +100 -0
- package/dist/quantization/scalar-quantization.d.ts.map +1 -0
- package/dist/quantization/scalar-quantization.js +324 -0
- package/dist/quantization/scalar-quantization.js.map +1 -0
- package/dist/quantization/scalar-quantization.mjs +319 -0
- package/dist/query/index.d.ts +6 -0
- package/dist/query/index.d.ts.map +1 -0
- package/dist/query/index.js +9 -0
- package/dist/query/index.js.map +1 -0
- package/dist/query/index.mjs +4 -0
- package/dist/query/query-builder.d.ts +323 -0
- package/dist/query/query-builder.d.ts.map +1 -0
- package/dist/query/query-builder.js +524 -0
- package/dist/query/query-builder.js.map +1 -0
- package/dist/query/query-builder.mjs +519 -0
- package/dist/reasoning/context-synthesizer.d.ts +57 -0
- package/dist/reasoning/context-synthesizer.d.ts.map +1 -0
- package/dist/reasoning/context-synthesizer.js +224 -0
- package/dist/reasoning/context-synthesizer.js.map +1 -0
- package/dist/reasoning/context-synthesizer.mjs +219 -0
- package/dist/reasoning/experience-curator.d.ts +66 -0
- package/dist/reasoning/experience-curator.d.ts.map +1 -0
- package/dist/reasoning/experience-curator.js +288 -0
- package/dist/reasoning/experience-curator.js.map +1 -0
- package/dist/reasoning/experience-curator.mjs +283 -0
- package/dist/reasoning/memory-optimizer.d.ts +69 -0
- package/dist/reasoning/memory-optimizer.d.ts.map +1 -0
- package/dist/reasoning/memory-optimizer.js +331 -0
- package/dist/reasoning/memory-optimizer.js.map +1 -0
- package/dist/reasoning/memory-optimizer.mjs +326 -0
- package/dist/reasoning/pattern-matcher.d.ts +59 -0
- package/dist/reasoning/pattern-matcher.d.ts.map +1 -0
- package/dist/reasoning/pattern-matcher.js +229 -0
- package/dist/reasoning/pattern-matcher.js.map +1 -0
- package/dist/reasoning/pattern-matcher.mjs +224 -0
- package/dist/reasoningbank/adapter/agentdb-adapter.d.ts +118 -0
- package/dist/reasoningbank/adapter/agentdb-adapter.d.ts.map +1 -0
- package/dist/reasoningbank/adapter/agentdb-adapter.js +477 -0
- package/dist/reasoningbank/adapter/agentdb-adapter.js.map +1 -0
- package/dist/reasoningbank/adapter/types.d.ts +113 -0
- package/dist/reasoningbank/adapter/types.d.ts.map +1 -0
- package/dist/reasoningbank/adapter/types.js +9 -0
- package/dist/reasoningbank/adapter/types.js.map +1 -0
- package/dist/reasoningbank/cli/commands.d.ts +16 -0
- package/dist/reasoningbank/cli/commands.d.ts.map +1 -0
- package/dist/reasoningbank/cli/commands.js +272 -0
- package/dist/reasoningbank/cli/commands.js.map +1 -0
- package/dist/reasoningbank/mcp/agentdb-tools.d.ts +319 -0
- package/dist/reasoningbank/mcp/agentdb-tools.d.ts.map +1 -0
- package/dist/reasoningbank/mcp/agentdb-tools.js +301 -0
- package/dist/reasoningbank/mcp/agentdb-tools.js.map +1 -0
- package/dist/reasoningbank/migration/migrate.d.ts +25 -0
- package/dist/reasoningbank/migration/migrate.d.ts.map +1 -0
- package/dist/reasoningbank/migration/migrate.js +178 -0
- package/dist/reasoningbank/migration/migrate.js.map +1 -0
- package/dist/reasoningbank/reasoning/context-synthesizer.d.ts +37 -0
- package/dist/reasoningbank/reasoning/context-synthesizer.d.ts.map +1 -0
- package/dist/reasoningbank/reasoning/context-synthesizer.js +114 -0
- package/dist/reasoningbank/reasoning/context-synthesizer.js.map +1 -0
- package/dist/reasoningbank/reasoning/experience-curator.d.ts +39 -0
- package/dist/reasoningbank/reasoning/experience-curator.d.ts.map +1 -0
- package/dist/reasoningbank/reasoning/experience-curator.js +98 -0
- package/dist/reasoningbank/reasoning/experience-curator.js.map +1 -0
- package/dist/reasoningbank/reasoning/memory-optimizer.d.ts +44 -0
- package/dist/reasoningbank/reasoning/memory-optimizer.d.ts.map +1 -0
- package/dist/reasoningbank/reasoning/memory-optimizer.js +184 -0
- package/dist/reasoningbank/reasoning/memory-optimizer.js.map +1 -0
- package/dist/reasoningbank/reasoning/pattern-matcher.d.ts +40 -0
- package/dist/reasoningbank/reasoning/pattern-matcher.d.ts.map +1 -0
- package/dist/reasoningbank/reasoning/pattern-matcher.js +87 -0
- package/dist/reasoningbank/reasoning/pattern-matcher.js.map +1 -0
- package/dist/reasoningbank/sync/quic-sync.d.ts +77 -0
- package/dist/reasoningbank/sync/quic-sync.d.ts.map +1 -0
- package/dist/reasoningbank/sync/quic-sync.js +165 -0
- package/dist/reasoningbank/sync/quic-sync.js.map +1 -0
- package/dist/sync/conflict.d.ts +78 -0
- package/dist/sync/conflict.d.ts.map +1 -0
- package/dist/sync/conflict.js +202 -0
- package/dist/sync/conflict.js.map +1 -0
- package/dist/sync/conflict.mjs +196 -0
- package/dist/sync/coordinator.d.ts +111 -0
- package/dist/sync/coordinator.d.ts.map +1 -0
- package/dist/sync/coordinator.js +256 -0
- package/dist/sync/coordinator.js.map +1 -0
- package/dist/sync/coordinator.mjs +250 -0
- package/dist/sync/delta.d.ts +81 -0
- package/dist/sync/delta.d.ts.map +1 -0
- package/dist/sync/delta.js +245 -0
- package/dist/sync/delta.js.map +1 -0
- package/dist/sync/delta.mjs +238 -0
- package/dist/sync/index.d.ts +11 -0
- package/dist/sync/index.d.ts.map +1 -0
- package/dist/sync/index.js +22 -0
- package/dist/sync/index.js.map +1 -0
- package/dist/sync/index.mjs +9 -0
- package/dist/sync/quic-sync.d.ts +81 -0
- package/dist/sync/quic-sync.d.ts.map +1 -0
- package/dist/sync/quic-sync.js +329 -0
- package/dist/sync/quic-sync.js.map +1 -0
- package/dist/sync/quic-sync.mjs +323 -0
- package/dist/sync/types.d.ts +168 -0
- package/dist/sync/types.d.ts.map +1 -0
- package/dist/sync/types.js +8 -0
- package/dist/sync/types.js.map +1 -0
- package/dist/sync/types.mjs +6 -0
- package/dist/types/index.d.ts +117 -0
- package/dist/types/index.d.ts.map +1 -0
- package/dist/types/index.js +6 -0
- package/dist/types/index.js.map +1 -0
- package/dist/types/index.mjs +4 -0
- package/dist/wasm-loader.d.ts +32 -0
- package/dist/wasm-loader.d.ts.map +1 -0
- package/dist/wasm-loader.js +75 -0
- package/dist/wasm-loader.js.map +1 -0
- package/dist/wasm-loader.mjs +64 -0
- package/examples/adaptive-learning.ts +284 -0
- package/examples/browser/README.md +732 -0
- package/examples/browser/adaptive-recommendations/index.html +427 -0
- package/examples/browser/collaborative-filtering/index.html +310 -0
- package/examples/browser/continual-learning/index.html +736 -0
- package/examples/browser/experience-replay/index.html +616 -0
- package/examples/browser/index.html +369 -0
- package/examples/browser/meta-learning/index.html +789 -0
- package/examples/browser/neuro-symbolic/index.html +692 -0
- package/examples/browser/pattern-learning/index.html +620 -0
- package/examples/browser/quantum-inspired/index.html +728 -0
- package/examples/browser/rag/index.html +624 -0
- package/examples/browser/swarm-intelligence/index.html +811 -0
- package/examples/browser-basic.html +170 -0
- package/examples/hnsw-example.ts +148 -0
- package/examples/node-basic.js +70 -0
- package/examples/quic-sync-example.ts +310 -0
- package/examples/quick-start.js +68 -0
- package/examples/wasm-example.ts +222 -0
- package/package.json +118 -0
|
@@ -0,0 +1,616 @@
|
|
|
1
|
+
<!DOCTYPE html>
|
|
2
|
+
<html lang="en">
|
|
3
|
+
<head>
|
|
4
|
+
<meta charset="UTF-8">
|
|
5
|
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
6
|
+
<title>Experience Replay Learning - AgentDB</title>
|
|
7
|
+
<style>
|
|
8
|
+
* { margin: 0; padding: 0; box-sizing: border-box; }
|
|
9
|
+
|
|
10
|
+
body {
|
|
11
|
+
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
|
|
12
|
+
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
|
13
|
+
min-height: 100vh;
|
|
14
|
+
padding: 2rem;
|
|
15
|
+
}
|
|
16
|
+
|
|
17
|
+
.container { max-width: 1400px; margin: 0 auto; }
|
|
18
|
+
|
|
19
|
+
header {
|
|
20
|
+
background: white;
|
|
21
|
+
border-radius: 12px;
|
|
22
|
+
padding: 2rem;
|
|
23
|
+
margin-bottom: 2rem;
|
|
24
|
+
box-shadow: 0 10px 30px rgba(0,0,0,0.2);
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
h1 { color: #333; margin-bottom: 0.5rem; }
|
|
28
|
+
.subtitle { color: #666; }
|
|
29
|
+
|
|
30
|
+
.grid { display: grid; grid-template-columns: 2fr 1fr; gap: 2rem; }
|
|
31
|
+
|
|
32
|
+
.card {
|
|
33
|
+
background: white;
|
|
34
|
+
border-radius: 12px;
|
|
35
|
+
padding: 2rem;
|
|
36
|
+
box-shadow: 0 10px 30px rgba(0,0,0,0.2);
|
|
37
|
+
}
|
|
38
|
+
|
|
39
|
+
.card h2 { color: #333; margin-bottom: 1rem; }
|
|
40
|
+
|
|
41
|
+
.game-board {
|
|
42
|
+
display: grid;
|
|
43
|
+
grid-template-columns: repeat(5, 1fr);
|
|
44
|
+
gap: 0.5rem;
|
|
45
|
+
margin: 1rem 0;
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
.cell {
|
|
49
|
+
aspect-ratio: 1;
|
|
50
|
+
background: #f0f0f0;
|
|
51
|
+
border: 2px solid #ddd;
|
|
52
|
+
border-radius: 6px;
|
|
53
|
+
display: flex;
|
|
54
|
+
align-items: center;
|
|
55
|
+
justify-content: center;
|
|
56
|
+
font-size: 1.5rem;
|
|
57
|
+
cursor: pointer;
|
|
58
|
+
transition: all 0.2s ease;
|
|
59
|
+
}
|
|
60
|
+
|
|
61
|
+
.cell:hover { background: #e0e0e0; transform: scale(1.05); }
|
|
62
|
+
.cell.agent { background: #667eea; color: white; }
|
|
63
|
+
.cell.goal { background: #28a745; color: white; }
|
|
64
|
+
.cell.obstacle { background: #dc3545; color: white; }
|
|
65
|
+
.cell.path { background: #667eea33; }
|
|
66
|
+
|
|
67
|
+
.controls {
|
|
68
|
+
display: grid;
|
|
69
|
+
grid-template-columns: repeat(3, 1fr);
|
|
70
|
+
gap: 0.5rem;
|
|
71
|
+
margin: 1rem 0;
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
.btn {
|
|
75
|
+
padding: 0.75rem 1rem;
|
|
76
|
+
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
|
77
|
+
color: white;
|
|
78
|
+
border: none;
|
|
79
|
+
border-radius: 6px;
|
|
80
|
+
font-weight: 600;
|
|
81
|
+
cursor: pointer;
|
|
82
|
+
transition: opacity 0.3s ease;
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
.btn:hover { opacity: 0.9; }
|
|
86
|
+
.btn.secondary {
|
|
87
|
+
background: #6c757d;
|
|
88
|
+
}
|
|
89
|
+
|
|
90
|
+
.stat-box {
|
|
91
|
+
background: #f8f9fa;
|
|
92
|
+
border-radius: 6px;
|
|
93
|
+
padding: 1rem;
|
|
94
|
+
margin-bottom: 0.5rem;
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
.stat-label { color: #666; font-size: 0.9rem; }
|
|
98
|
+
.stat-value {
|
|
99
|
+
color: #333;
|
|
100
|
+
font-size: 1.5rem;
|
|
101
|
+
font-weight: bold;
|
|
102
|
+
margin-top: 0.25rem;
|
|
103
|
+
}
|
|
104
|
+
|
|
105
|
+
.progress-bar {
|
|
106
|
+
width: 100%;
|
|
107
|
+
height: 20px;
|
|
108
|
+
background: #e0e0e0;
|
|
109
|
+
border-radius: 10px;
|
|
110
|
+
overflow: hidden;
|
|
111
|
+
margin-top: 0.5rem;
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
.progress-fill {
|
|
115
|
+
height: 100%;
|
|
116
|
+
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
|
|
117
|
+
transition: width 0.3s ease;
|
|
118
|
+
}
|
|
119
|
+
|
|
120
|
+
.experience-list {
|
|
121
|
+
max-height: 300px;
|
|
122
|
+
overflow-y: auto;
|
|
123
|
+
background: #f8f9fa;
|
|
124
|
+
border-radius: 6px;
|
|
125
|
+
padding: 1rem;
|
|
126
|
+
}
|
|
127
|
+
|
|
128
|
+
.experience-item {
|
|
129
|
+
background: white;
|
|
130
|
+
border-radius: 4px;
|
|
131
|
+
padding: 0.75rem;
|
|
132
|
+
margin-bottom: 0.5rem;
|
|
133
|
+
font-size: 0.85rem;
|
|
134
|
+
border-left: 3px solid #667eea;
|
|
135
|
+
}
|
|
136
|
+
|
|
137
|
+
.reward-positive { border-left-color: #28a745; }
|
|
138
|
+
.reward-negative { border-left-color: #dc3545; }
|
|
139
|
+
|
|
140
|
+
.q-values {
|
|
141
|
+
display: grid;
|
|
142
|
+
grid-template-columns: repeat(2, 1fr);
|
|
143
|
+
gap: 0.5rem;
|
|
144
|
+
margin-top: 1rem;
|
|
145
|
+
}
|
|
146
|
+
|
|
147
|
+
.q-value {
|
|
148
|
+
background: #f8f9fa;
|
|
149
|
+
padding: 0.75rem;
|
|
150
|
+
border-radius: 6px;
|
|
151
|
+
text-align: center;
|
|
152
|
+
}
|
|
153
|
+
|
|
154
|
+
.q-label { color: #666; font-size: 0.85rem; }
|
|
155
|
+
.q-number {
|
|
156
|
+
color: #333;
|
|
157
|
+
font-size: 1.2rem;
|
|
158
|
+
font-weight: bold;
|
|
159
|
+
margin-top: 0.25rem;
|
|
160
|
+
}
|
|
161
|
+
|
|
162
|
+
.training-log {
|
|
163
|
+
background: #f8f9fa;
|
|
164
|
+
border-radius: 6px;
|
|
165
|
+
padding: 1rem;
|
|
166
|
+
font-family: 'Courier New', monospace;
|
|
167
|
+
font-size: 0.85rem;
|
|
168
|
+
max-height: 200px;
|
|
169
|
+
overflow-y: auto;
|
|
170
|
+
}
|
|
171
|
+
|
|
172
|
+
.log-entry {
|
|
173
|
+
margin-bottom: 0.25rem;
|
|
174
|
+
color: #333;
|
|
175
|
+
}
|
|
176
|
+
|
|
177
|
+
.log-success { color: #28a745; }
|
|
178
|
+
.log-fail { color: #dc3545; }
|
|
179
|
+
</style>
|
|
180
|
+
</head>
|
|
181
|
+
<body>
|
|
182
|
+
<div class="container">
|
|
183
|
+
<header>
|
|
184
|
+
<h1>🎮 Experience Replay Learning</h1>
|
|
185
|
+
<p class="subtitle">Q-Learning with Experience Buffer and Neural Pattern Training</p>
|
|
186
|
+
</header>
|
|
187
|
+
|
|
188
|
+
<div class="grid">
|
|
189
|
+
<div>
|
|
190
|
+
<div class="card" style="margin-bottom: 1rem;">
|
|
191
|
+
<h2>Grid World Environment</h2>
|
|
192
|
+
<p style="color: #666; margin-bottom: 1rem;">
|
|
193
|
+
Navigate to the goal 🎯. Avoid obstacles ⛔. Learn optimal paths!
|
|
194
|
+
</p>
|
|
195
|
+
|
|
196
|
+
<div class="game-board" id="gameBoard"></div>
|
|
197
|
+
|
|
198
|
+
<div class="controls">
|
|
199
|
+
<button class="btn" id="upBtn">⬆️ Up</button>
|
|
200
|
+
<button class="btn" id="trainBtn">🧠 Train Agent</button>
|
|
201
|
+
<button class="btn" id="downBtn">⬇️ Down</button>
|
|
202
|
+
<button class="btn" id="leftBtn">⬅️ Left</button>
|
|
203
|
+
<button class="btn" id="autoBtn">🤖 Auto Play</button>
|
|
204
|
+
<button class="btn" id="rightBtn">➡️ Right</button>
|
|
205
|
+
</div>
|
|
206
|
+
|
|
207
|
+
<div class="btn" style="margin-top: 1rem; width: 100%; text-align: center;" id="resetBtn">
|
|
208
|
+
🔄 Reset Environment
|
|
209
|
+
</div>
|
|
210
|
+
</div>
|
|
211
|
+
|
|
212
|
+
<div class="card">
|
|
213
|
+
<h2>Experience Buffer (Last 10)</h2>
|
|
214
|
+
<div class="experience-list" id="experienceList">
|
|
215
|
+
<p style="color: #666; text-align: center;">No experiences yet</p>
|
|
216
|
+
</div>
|
|
217
|
+
</div>
|
|
218
|
+
</div>
|
|
219
|
+
|
|
220
|
+
<div>
|
|
221
|
+
<div class="card" style="margin-bottom: 1rem;">
|
|
222
|
+
<h2>Learning Progress</h2>
|
|
223
|
+
|
|
224
|
+
<div class="stat-box">
|
|
225
|
+
<div class="stat-label">Episodes Completed</div>
|
|
226
|
+
<div class="stat-value" id="episodes">0</div>
|
|
227
|
+
</div>
|
|
228
|
+
|
|
229
|
+
<div class="stat-box">
|
|
230
|
+
<div class="stat-label">Success Rate</div>
|
|
231
|
+
<div class="stat-value" id="successRate">0%</div>
|
|
232
|
+
<div class="progress-bar">
|
|
233
|
+
<div class="progress-fill" id="successProgress" style="width: 0%"></div>
|
|
234
|
+
</div>
|
|
235
|
+
</div>
|
|
236
|
+
|
|
237
|
+
<div class="stat-box">
|
|
238
|
+
<div class="stat-label">Avg Steps to Goal</div>
|
|
239
|
+
<div class="stat-value" id="avgSteps">-</div>
|
|
240
|
+
</div>
|
|
241
|
+
|
|
242
|
+
<div class="stat-box">
|
|
243
|
+
<div class="stat-label">Total Experiences</div>
|
|
244
|
+
<div class="stat-value" id="totalExp">0</div>
|
|
245
|
+
</div>
|
|
246
|
+
</div>
|
|
247
|
+
|
|
248
|
+
<div class="card" style="margin-bottom: 1rem;">
|
|
249
|
+
<h2>Q-Values (Current State)</h2>
|
|
250
|
+
<div class="q-values">
|
|
251
|
+
<div class="q-value">
|
|
252
|
+
<div class="q-label">Up ⬆️</div>
|
|
253
|
+
<div class="q-number" id="qUp">0.00</div>
|
|
254
|
+
</div>
|
|
255
|
+
<div class="q-value">
|
|
256
|
+
<div class="q-label">Down ⬇️</div>
|
|
257
|
+
<div class="q-number" id="qDown">0.00</div>
|
|
258
|
+
</div>
|
|
259
|
+
<div class="q-value">
|
|
260
|
+
<div class="q-label">Left ⬅️</div>
|
|
261
|
+
<div class="q-number" id="qLeft">0.00</div>
|
|
262
|
+
</div>
|
|
263
|
+
<div class="q-value">
|
|
264
|
+
<div class="q-label">Right ➡️</div>
|
|
265
|
+
<div class="q-number" id="qRight">0.00</div>
|
|
266
|
+
</div>
|
|
267
|
+
</div>
|
|
268
|
+
</div>
|
|
269
|
+
|
|
270
|
+
<div class="card">
|
|
271
|
+
<h2>Training Log</h2>
|
|
272
|
+
<div class="training-log" id="trainingLog">
|
|
273
|
+
<div class="log-entry">Ready to start training...</div>
|
|
274
|
+
</div>
|
|
275
|
+
</div>
|
|
276
|
+
</div>
|
|
277
|
+
</div>
|
|
278
|
+
</div>
|
|
279
|
+
|
|
280
|
+
<script type="module">
|
|
281
|
+
/**
|
|
282
|
+
* Experience Replay Q-Learning Example
|
|
283
|
+
*
|
|
284
|
+
* Demonstrates:
|
|
285
|
+
* 1. Experience buffer management
|
|
286
|
+
* 2. Q-learning with replay
|
|
287
|
+
* 3. Exploration vs exploitation
|
|
288
|
+
* 4. Policy improvement over time
|
|
289
|
+
*/
|
|
290
|
+
|
|
291
|
+
const GRID_SIZE = 5;
|
|
292
|
+
const ACTIONS = ['up', 'down', 'left', 'right'];
|
|
293
|
+
|
|
294
|
+
let state = { x: 0, y: 0 };
|
|
295
|
+
let goal = { x: 4, y: 4 };
|
|
296
|
+
let obstacles = [{ x: 1, y: 1 }, { x: 2, y: 2 }, { x: 3, y: 1 }];
|
|
297
|
+
let experienceBuffer = [];
|
|
298
|
+
let qTable = {};
|
|
299
|
+
let episodes = 0;
|
|
300
|
+
let successes = 0;
|
|
301
|
+
let stepHistory = [];
|
|
302
|
+
let autoPlaying = false;
|
|
303
|
+
|
|
304
|
+
// Hyperparameters
|
|
305
|
+
const ALPHA = 0.1; // Learning rate
|
|
306
|
+
const GAMMA = 0.9; // Discount factor
|
|
307
|
+
const EPSILON = 0.1; // Exploration rate
|
|
308
|
+
const BUFFER_SIZE = 100;
|
|
309
|
+
|
|
310
|
+
function initGrid() {
|
|
311
|
+
const board = document.getElementById('gameBoard');
|
|
312
|
+
board.innerHTML = '';
|
|
313
|
+
|
|
314
|
+
for (let y = 0; y < GRID_SIZE; y++) {
|
|
315
|
+
for (let x = 0; x < GRID_SIZE; x++) {
|
|
316
|
+
const cell = document.createElement('div');
|
|
317
|
+
cell.className = 'cell';
|
|
318
|
+
cell.dataset.x = x;
|
|
319
|
+
cell.dataset.y = y;
|
|
320
|
+
|
|
321
|
+
if (x === state.x && y === state.y) {
|
|
322
|
+
cell.classList.add('agent');
|
|
323
|
+
cell.textContent = '🤖';
|
|
324
|
+
} else if (x === goal.x && y === goal.y) {
|
|
325
|
+
cell.classList.add('goal');
|
|
326
|
+
cell.textContent = '🎯';
|
|
327
|
+
} else if (obstacles.some(o => o.x === x && o.y === y)) {
|
|
328
|
+
cell.classList.add('obstacle');
|
|
329
|
+
cell.textContent = '⛔';
|
|
330
|
+
}
|
|
331
|
+
|
|
332
|
+
board.appendChild(cell);
|
|
333
|
+
}
|
|
334
|
+
}
|
|
335
|
+
|
|
336
|
+
updateQValues();
|
|
337
|
+
}
|
|
338
|
+
|
|
339
|
+
function getStateKey(s) {
|
|
340
|
+
return `${s.x},${s.y}`;
|
|
341
|
+
}
|
|
342
|
+
|
|
343
|
+
function getQValue(stateKey, action) {
|
|
344
|
+
if (!qTable[stateKey]) {
|
|
345
|
+
qTable[stateKey] = { up: 0, down: 0, left: 0, right: 0 };
|
|
346
|
+
}
|
|
347
|
+
return qTable[stateKey][action];
|
|
348
|
+
}
|
|
349
|
+
|
|
350
|
+
function setQValue(stateKey, action, value) {
|
|
351
|
+
if (!qTable[stateKey]) {
|
|
352
|
+
qTable[stateKey] = { up: 0, down: 0, left: 0, right: 0 };
|
|
353
|
+
}
|
|
354
|
+
qTable[stateKey][action] = value;
|
|
355
|
+
}
|
|
356
|
+
|
|
357
|
+
function chooseAction(stateKey) {
|
|
358
|
+
// Epsilon-greedy policy
|
|
359
|
+
if (Math.random() < EPSILON) {
|
|
360
|
+
// Explore: random action
|
|
361
|
+
return ACTIONS[Math.floor(Math.random() * ACTIONS.length)];
|
|
362
|
+
} else {
|
|
363
|
+
// Exploit: best known action
|
|
364
|
+
let maxQ = -Infinity;
|
|
365
|
+
let bestAction = ACTIONS[0];
|
|
366
|
+
|
|
367
|
+
for (const action of ACTIONS) {
|
|
368
|
+
const q = getQValue(stateKey, action);
|
|
369
|
+
if (q > maxQ) {
|
|
370
|
+
maxQ = q;
|
|
371
|
+
bestAction = action;
|
|
372
|
+
}
|
|
373
|
+
}
|
|
374
|
+
|
|
375
|
+
return bestAction;
|
|
376
|
+
}
|
|
377
|
+
}
|
|
378
|
+
|
|
379
|
+
function takeAction(action) {
|
|
380
|
+
const newState = { ...state };
|
|
381
|
+
|
|
382
|
+
switch (action) {
|
|
383
|
+
case 'up': newState.y = Math.max(0, newState.y - 1); break;
|
|
384
|
+
case 'down': newState.y = Math.min(GRID_SIZE - 1, newState.y + 1); break;
|
|
385
|
+
case 'left': newState.x = Math.max(0, newState.x - 1); break;
|
|
386
|
+
case 'right': newState.x = Math.min(GRID_SIZE - 1, newState.x + 1); break;
|
|
387
|
+
}
|
|
388
|
+
|
|
389
|
+
// Calculate reward
|
|
390
|
+
let reward = -0.1; // Small penalty for each step
|
|
391
|
+
let done = false;
|
|
392
|
+
|
|
393
|
+
if (newState.x === goal.x && newState.y === goal.y) {
|
|
394
|
+
reward = 10; // Big reward for reaching goal
|
|
395
|
+
done = true;
|
|
396
|
+
} else if (obstacles.some(o => o.x === newState.x && o.y === newState.y)) {
|
|
397
|
+
reward = -5; // Penalty for hitting obstacle
|
|
398
|
+
newState.x = state.x;
|
|
399
|
+
newState.y = state.y;
|
|
400
|
+
}
|
|
401
|
+
|
|
402
|
+
// Store experience
|
|
403
|
+
const experience = {
|
|
404
|
+
state: getStateKey(state),
|
|
405
|
+
action: action,
|
|
406
|
+
reward: reward,
|
|
407
|
+
nextState: getStateKey(newState),
|
|
408
|
+
done: done,
|
|
409
|
+
timestamp: Date.now()
|
|
410
|
+
};
|
|
411
|
+
|
|
412
|
+
addExperience(experience);
|
|
413
|
+
|
|
414
|
+
state = newState;
|
|
415
|
+
initGrid();
|
|
416
|
+
|
|
417
|
+
return { reward, done };
|
|
418
|
+
}
|
|
419
|
+
|
|
420
|
+
function addExperience(exp) {
|
|
421
|
+
experienceBuffer.unshift(exp);
|
|
422
|
+
if (experienceBuffer.length > BUFFER_SIZE) {
|
|
423
|
+
experienceBuffer.pop();
|
|
424
|
+
}
|
|
425
|
+
|
|
426
|
+
renderExperiences();
|
|
427
|
+
document.getElementById('totalExp').textContent = experienceBuffer.length;
|
|
428
|
+
}
|
|
429
|
+
|
|
430
|
+
function trainFromReplay(batchSize = 10) {
|
|
431
|
+
if (experienceBuffer.length < batchSize) return;
|
|
432
|
+
|
|
433
|
+
// Sample random batch from buffer
|
|
434
|
+
const batch = [];
|
|
435
|
+
for (let i = 0; i < batchSize; i++) {
|
|
436
|
+
const idx = Math.floor(Math.random() * experienceBuffer.length);
|
|
437
|
+
batch.push(experienceBuffer[idx]);
|
|
438
|
+
}
|
|
439
|
+
|
|
440
|
+
// Update Q-values
|
|
441
|
+
for (const exp of batch) {
|
|
442
|
+
let target = exp.reward;
|
|
443
|
+
|
|
444
|
+
if (!exp.done) {
|
|
445
|
+
// Q-learning: max future Q-value
|
|
446
|
+
let maxNextQ = -Infinity;
|
|
447
|
+
for (const action of ACTIONS) {
|
|
448
|
+
const q = getQValue(exp.nextState, action);
|
|
449
|
+
maxNextQ = Math.max(maxNextQ, q);
|
|
450
|
+
}
|
|
451
|
+
target += GAMMA * maxNextQ;
|
|
452
|
+
}
|
|
453
|
+
|
|
454
|
+
const currentQ = getQValue(exp.state, exp.action);
|
|
455
|
+
const newQ = currentQ + ALPHA * (target - currentQ);
|
|
456
|
+
setQValue(exp.state, exp.action, newQ);
|
|
457
|
+
}
|
|
458
|
+
|
|
459
|
+
updateQValues();
|
|
460
|
+
logTraining(`Trained on ${batchSize} experiences`);
|
|
461
|
+
}
|
|
462
|
+
|
|
463
|
+
async function autoPlay() {
|
|
464
|
+
autoPlaying = !autoPlaying;
|
|
465
|
+
const btn = document.getElementById('autoBtn');
|
|
466
|
+
|
|
467
|
+
if (autoPlaying) {
|
|
468
|
+
btn.textContent = '⏸️ Stop';
|
|
469
|
+
btn.classList.add('secondary');
|
|
470
|
+
|
|
471
|
+
while (autoPlaying) {
|
|
472
|
+
const stateKey = getStateKey(state);
|
|
473
|
+
const action = chooseAction(stateKey);
|
|
474
|
+
const { reward, done } = takeAction(action);
|
|
475
|
+
|
|
476
|
+
if (done) {
|
|
477
|
+
episodes++;
|
|
478
|
+
if (reward > 0) {
|
|
479
|
+
successes++;
|
|
480
|
+
logTraining(`✓ Episode ${episodes}: Reached goal`, 'success');
|
|
481
|
+
} else {
|
|
482
|
+
logTraining(`✗ Episode ${episodes}: Failed`, 'fail');
|
|
483
|
+
}
|
|
484
|
+
|
|
485
|
+
stepHistory.push(experienceBuffer.filter(e =>
|
|
486
|
+
e.timestamp > Date.now() - 5000
|
|
487
|
+
).length);
|
|
488
|
+
|
|
489
|
+
// Train after each episode
|
|
490
|
+
trainFromReplay(10);
|
|
491
|
+
|
|
492
|
+
updateStats();
|
|
493
|
+
|
|
494
|
+
// Reset
|
|
495
|
+
state = { x: 0, y: 0 };
|
|
496
|
+
initGrid();
|
|
497
|
+
|
|
498
|
+
await sleep(500);
|
|
499
|
+
}
|
|
500
|
+
|
|
501
|
+
await sleep(100);
|
|
502
|
+
}
|
|
503
|
+
} else {
|
|
504
|
+
btn.textContent = '🤖 Auto Play';
|
|
505
|
+
btn.classList.remove('secondary');
|
|
506
|
+
}
|
|
507
|
+
}
|
|
508
|
+
|
|
509
|
+
function sleep(ms) {
|
|
510
|
+
return new Promise(resolve => setTimeout(resolve, ms));
|
|
511
|
+
}
|
|
512
|
+
|
|
513
|
+
function updateQValues() {
|
|
514
|
+
const stateKey = getStateKey(state);
|
|
515
|
+
document.getElementById('qUp').textContent = getQValue(stateKey, 'up').toFixed(2);
|
|
516
|
+
document.getElementById('qDown').textContent = getQValue(stateKey, 'down').toFixed(2);
|
|
517
|
+
document.getElementById('qLeft').textContent = getQValue(stateKey, 'left').toFixed(2);
|
|
518
|
+
document.getElementById('qRight').textContent = getQValue(stateKey, 'right').toFixed(2);
|
|
519
|
+
}
|
|
520
|
+
|
|
521
|
+
function renderExperiences() {
|
|
522
|
+
const list = document.getElementById('experienceList');
|
|
523
|
+
|
|
524
|
+
if (experienceBuffer.length === 0) {
|
|
525
|
+
list.innerHTML = '<p style="color: #666; text-align: center;">No experiences yet</p>';
|
|
526
|
+
return;
|
|
527
|
+
}
|
|
528
|
+
|
|
529
|
+
const recent = experienceBuffer.slice(0, 10);
|
|
530
|
+
list.innerHTML = recent.map(exp => {
|
|
531
|
+
const rewardClass = exp.reward > 0 ? 'reward-positive' : exp.reward < -1 ? 'reward-negative' : '';
|
|
532
|
+
return `
|
|
533
|
+
<div class="experience-item ${rewardClass}">
|
|
534
|
+
State: ${exp.state} | Action: ${exp.action} | Reward: ${exp.reward.toFixed(2)}
|
|
535
|
+
</div>
|
|
536
|
+
`;
|
|
537
|
+
}).join('');
|
|
538
|
+
}
|
|
539
|
+
|
|
540
|
+
function updateStats() {
|
|
541
|
+
document.getElementById('episodes').textContent = episodes;
|
|
542
|
+
|
|
543
|
+
if (episodes > 0) {
|
|
544
|
+
const rate = (successes / episodes * 100).toFixed(0);
|
|
545
|
+
document.getElementById('successRate').textContent = `${rate}%`;
|
|
546
|
+
document.getElementById('successProgress').style.width = `${rate}%`;
|
|
547
|
+
}
|
|
548
|
+
|
|
549
|
+
if (stepHistory.length > 0) {
|
|
550
|
+
const avg = stepHistory.reduce((a, b) => a + b, 0) / stepHistory.length;
|
|
551
|
+
document.getElementById('avgSteps').textContent = avg.toFixed(1);
|
|
552
|
+
}
|
|
553
|
+
}
|
|
554
|
+
|
|
555
|
+
function logTraining(message, type = '') {
|
|
556
|
+
const log = document.getElementById('trainingLog');
|
|
557
|
+
const entry = document.createElement('div');
|
|
558
|
+
entry.className = `log-entry ${type ? 'log-' + type : ''}`;
|
|
559
|
+
entry.textContent = `[${new Date().toLocaleTimeString()}] ${message}`;
|
|
560
|
+
log.insertBefore(entry, log.firstChild);
|
|
561
|
+
|
|
562
|
+
// Keep only last 20 entries
|
|
563
|
+
while (log.children.length > 20) {
|
|
564
|
+
log.removeChild(log.lastChild);
|
|
565
|
+
}
|
|
566
|
+
}
|
|
567
|
+
|
|
568
|
+
function reset() {
|
|
569
|
+
state = { x: 0, y: 0 };
|
|
570
|
+
experienceBuffer = [];
|
|
571
|
+
qTable = {};
|
|
572
|
+
episodes = 0;
|
|
573
|
+
successes = 0;
|
|
574
|
+
stepHistory = [];
|
|
575
|
+
|
|
576
|
+
initGrid();
|
|
577
|
+
renderExperiences();
|
|
578
|
+
updateStats();
|
|
579
|
+
updateQValues();
|
|
580
|
+
|
|
581
|
+
document.getElementById('trainingLog').innerHTML = '<div class="log-entry">Environment reset</div>';
|
|
582
|
+
}
|
|
583
|
+
|
|
584
|
+
// Event listeners
|
|
585
|
+
document.getElementById('upBtn').addEventListener('click', () => {
|
|
586
|
+
const { reward, done } = takeAction('up');
|
|
587
|
+
if (done) { state = { x: 0, y: 0 }; initGrid(); }
|
|
588
|
+
});
|
|
589
|
+
|
|
590
|
+
document.getElementById('downBtn').addEventListener('click', () => {
|
|
591
|
+
const { reward, done } = takeAction('down');
|
|
592
|
+
if (done) { state = { x: 0, y: 0 }; initGrid(); }
|
|
593
|
+
});
|
|
594
|
+
|
|
595
|
+
document.getElementById('leftBtn').addEventListener('click', () => {
|
|
596
|
+
const { reward, done } = takeAction('left');
|
|
597
|
+
if (done) { state = { x: 0, y: 0 }; initGrid(); }
|
|
598
|
+
});
|
|
599
|
+
|
|
600
|
+
document.getElementById('rightBtn').addEventListener('click', () => {
|
|
601
|
+
const { reward, done } = takeAction('right');
|
|
602
|
+
if (done) { state = { x: 0, y: 0 }; initGrid(); }
|
|
603
|
+
});
|
|
604
|
+
|
|
605
|
+
document.getElementById('trainBtn').addEventListener('click', () => {
|
|
606
|
+
trainFromReplay(20);
|
|
607
|
+
});
|
|
608
|
+
|
|
609
|
+
document.getElementById('autoBtn').addEventListener('click', autoPlay);
|
|
610
|
+
document.getElementById('resetBtn').addEventListener('click', reset);
|
|
611
|
+
|
|
612
|
+
// Initialize
|
|
613
|
+
initGrid();
|
|
614
|
+
</script>
|
|
615
|
+
</body>
|
|
616
|
+
</html>
|