cogames 0.3.49__py3-none-any.whl → 0.3.64__py3-none-any.whl

cogames-0.3.49.dist-info/METADATA

@@ -1,406 +0,0 @@
-Metadata-Version: 2.4
-Name: cogames
-Version: 0.3.49
-Summary: Multi-agent cooperative games
-Requires-Python: <3.13,>=3.12
-Description-Content-Type: text/markdown
-Requires-Dist: heavyball>=2.0.0
-Requires-Dist: mettagrid==0.2.0.58
-Requires-Dist: packaging>=24.0.0
-Requires-Dist: pufferlib-core
-Requires-Dist: pydantic>=2.11.5
-Requires-Dist: pyyaml>=6.0.2
-Requires-Dist: einops>=0.8.0
-Requires-Dist: scipy>=1.15.3
-Requires-Dist: typer>=0.19.2
-Requires-Dist: rich>=13.7.0
-Requires-Dist: fastapi>=0.115.0
-Requires-Dist: uvicorn>=0.34.0
-Requires-Dist: httpx>=0.28.1
-
-# CoGames: A Game Environment for the Alignment League Benchmark
-
-CoGames is the game environment for Softmax's
-[Alignment League Benchmark (ALB)](https://www.softmax.com/alignmentleague) — a suite of multi-agent games designed to
-measure how well AI agents align, coordinate, and collaborate with others (both AIs and humans).
-
-The first ALB game, Cogs vs Clips, is implemented entirely within the CoGames environment. You can create your own
-policy and submit it to our benchmark/pool.
-
-## The game: Cogs vs Clips
-
-Cogs vs Clips is a cooperative production-and-survival game where teams of AI agents ("Cogs") work together on the
-asteroid Machina VII. Their mission: Produce and protect **HEARTs** (Holon Enabled Agent Replication Templates) by
-gathering resources, operating machinery, and assembling components. Success is impossible alone! Completing these
-missions requires multiple cogs working in tandem.
-
-<p align="middle">
-<img src="assets/cvc-reel.gif" alt="Example Cogs vs Clips">
-<br>
-
-There are many mission configurations available, with different map sizes, resource and station layouts, and game rules.
-Cogs should refer to their [MISSION.md](MISSION.md) for a thorough description of the game mechanics. Overall, Cogs vs
-Clips aims to present rich environments with:
-
-- **Resource management**: Energy, materials (carbon, oxygen, germanium, silicon), and crafted components
-- **Station-based interactions**: Different stations provide unique capabilities (extractors, assemblers, chargers,
-  chests)
-- **Sparse rewards**: Agents receive rewards only upon successfully crafting target items (hearts)
-- **Partial observability**: Agents have limited visibility of the environment
-- **Required multi-agent cooperation**: Agents must coordinate to efficiently use shared resources and stations, while
-  only communicating through movement and emotes (❤️, 🔄, 💯, etc.)
-
-Once your policy is successfully assembling hearts, submit it to our Alignment League Benchmark. ALB evaluates how your
-policy plays with other policies in the pool through running multi-policy, multi-agent games. Our focal metric is VORP
-(Value Over Replacement Policy), an estimate of how much your agent improves team performance in scoring hearts.
-
-# Get Started
-
-## Step 1: Set up and install
-
-Install [cogames](https://pypi.org/project/cogames/) as a Python package.
-
-```bash
-# We recommend using a virtual env
-curl -LsSf https://astral.sh/uv/install.sh | sh
-uv venv .venv
-source .venv/bin/activate
-
-# Install cogames
-uv pip install cogames
-```
-
-## Step 2: Game tutorial
-
-Play an easy mission in Cogs vs. Clips using `cogames tutorial play`. Follow the instructions given in the terminal,
-while you use the GUI to accomplish your first training mission.
-
-## Step 3: Train a simple policy
-
-We'll train a simple starter policy on `training_facility.harvest`. Optional variants to simplify training:
-
-- `lonely_heart` - Simplifies heart crafting to require only 1 of each resource (carbon, oxygen, germanium, silicon,
-  energy)
-- `heart_chorus` - Provides reward shaping that gives bonuses for gaining hearts and maintaining diverse inventories
-- `pack_rat` - Raises all capacity limits (heart, cargo, energy, gear) to 255 so agents never run out of storage space
-
-```bash
-# Play an episode of the training_facility.harvest mission with a scripted policy
-cogames play -m training_facility.harvest -p class=baseline
-
-# Try the scripted policy on a set of eval missions
-cogames run -S integrated_evals -p class=baseline
-
-# Train with an LSTM policy on training_facility.harvest
-cogames tutorial train -m training_facility.harvest -p class=lstm
-```
-
-## Step 4: Learn about missions
-
-Get familiar with different missions in Cogs vs. Clips so you can develop a policy that's able to handle different
-scenarios.
-
-Useful commands to explore:
-
-```bash
-# List available missions
-cogames missions
-
-# Describe a specific mission in detail
-cogames missions -m [MISSION]
-
-# List available variants for modifying missions
-cogames variants
-
-# List all missions used as evals for analyzing the behaviour of agents
-cogames evals
-
-# Shows all policies available and their shorthands
-cogames policies
-
-# Authenticate before uploading or checking leaderboard
-cogames login
-
-# List available tournament seasons
-cogames seasons
-
-# View leaderboard for a season
-cogames leaderboard --season SEASON
-
-# View your tournament submissions
-cogames submissions
-```
-
-# Develop a Policy
-
-A **policy** contains the decision-making logic that controls your agents. Given an observation of the game state, a
-policy outputs an action.
-
-CoGames asks that policies implement the `MultiAgentPolicy` interface. Any implementation will work, and we provide two
-templates to get you up and running:
-
-- `cogames tutorial make-policy --scripted` gives a starter template for a simple, rule-based script
-- `cogames tutorial make-policy --trainable` gives a basic neural-net based implementation that can be trained via
-  `cogames tutorial train`
-
-## Play, Train, and Run
-
-Most commands are of the form `cogames <command> -m [MISSION] -p [POLICY] [OPTIONS]`
-
-To specify a `MISSION`, you can:
-
-- Use a mission name from the registry given by `cogames missions`, e.g. `training_facility_1`.
-- Use a path to a mission configuration file, e.g. `path/to/mission.yaml`.
-- Alternatively, specify a set of missions with `-S` or `--mission-set`.
-
-To specify a `POLICY`, use one of two formats:
-
-**URI format** (for checkpoint bundles):
-
-- Point directly at a checkpoint bundle (directory or `.zip` containing `policy_spec.json`)
-- Examples: `./train_dir/my_run:v5`, `./train_dir/my_run:v5.zip`, `s3://bucket/path/run:v5.zip`
-- Use `:latest` suffix to auto-resolve the highest epoch: `./train_dir/checkpoints:latest`
-
-**Key-value format** (for explicit class + weights):
-
-- `class=`: Policy shorthand or full class path from `cogames policies`, e.g. `class=lstm` or
-  `class=cogames.policy.random.RandomPolicy`.
-- `data=`: Optional path to a weights file (e.g., `weights.safetensors`). Must be a file, not a directory.
-- `proportion=`: Optional positive float specifying the relative share of agents that use this policy (default: 1.0).
-- `kw.<arg>=`: Optional policy `__init__` keyword arguments (all values parsed as strings).
-
-### `cogames play -m [MISSION] -p [POLICY]`
-
-Play an episode of the specified mission.
-
-Cogs' actions are determined by the provided policy, except if you take over their actions manually.
-
-If not specified, this command will use the `noop`-policy agent -- do not be surprised if when you play you don't see
-other agents moving around! Just provide a different policy, like `random`.
-
-**Options:**
-
-- `--steps N`: Number of steps (default: 10000)
-- `--render MODE`: 'gui' or 'text' (default: gui)
-- `--non-interactive`: Non-interactive mode (default: false)
-
-`cogames play` supports a gui-based and text-based game renderer, both of which support many features to inspect agents
-and manually play alongside them.
-
-### `cogames tutorial train -m [MISSION] -p [POLICY]`
-
-Train a policy on a mission.
-
-By default, our `stateless` policy architecture will be used. But as is explained above, you can select a different
-policy architecture we support out of the box (like `lstm`), or can define your own and supply a path to it.
-
-Any policy provided must implement the `MultiAgentPolicy` interface with a trainable `network()` method, which you can
-find in `mettagrid/policy/policy.py`.
-
-You can continue training from a checkpoint bundle (use URI format):
-
-```
-cogames tutorial train -m [MISSION] -p ./train_dir/my_run:v5
-```
-
-Or load weights into an explicit class:
-
-```
-cogames tutorial train -m [MISSION] -p class=path.to.MyPolicy,data=train_dir/run:v5/weights.safetensors
-```
-
-Note that you can supply repeated `-m` missions. This yields a training curriculum that rotates through those
-environments:
-
-```
-cogames tutorial train -m training_facility_1 -m training_facility_2 -p class=stateless
-```
-
-You can also specify multiple missions with `*` wildcards:
-
-- `cogames tutorial train -m 'machina_2_bigger:*'` will specify all missions on the machina_2_bigger map
-- `cogames tutorial train -m '*:shaped'` will specify all "shaped" missions across all maps
-- `cogames tutorial train -m 'machina*:shaped'` will specify all "shaped" missions on all machina maps
-
-**Options:**
-
-- `--steps N`: Training steps (default: 10000)
-- `--device STR`: 'auto', 'cpu', or 'cuda' (default: auto)
-- `--batch-size N`: Batch size (default: 4096)
-- `--num-workers N`: Worker processes (default: CPU count)
-
-### Custom Policy Architectures
-
-CoGames supports torch-based policy architectures out of the box (such as `stateless` and `lstm`). To create your own
-trainable policy, run:
-
-```bash
-cogames tutorial make-policy --trainable -o my_policy.py
-```
-
-This generates a complete working template. See the
-[trainable policy template](src/cogames/policy/trainable_policy_template.py) for the full implementation. The key
-components are:
-
-- **`MultiAgentPolicy`**: The main policy class that the training system interacts with
-- **`AgentPolicy`**: Per-agent decision-making (returned by `agent_policy()`)
-- **`network()`**: Returns the `nn.Module` for training (must implement `forward_eval(obs, state) -> (logits, values)`)
-- **`load_policy_data()` / `save_policy_data()`**: Checkpoint serialization
-
-To train using your policy:
-
-```bash
-cogames tutorial train -m training_facility.harvest -p class=my_policy.MyTrainablePolicy
-```
-
-#### Environment API
-
-The underlying environment follows the Gymnasium API:
-
-```python
-from cogames.cli.mission import get_mission
-from mettagrid import PufferMettaGridEnv
-from mettagrid.simulator import Simulator
-
-# Load a mission configuration
-_, config = get_mission("machina_1.open_world")
-
-# Create environment
-simulator = Simulator()
-env = PufferMettaGridEnv(simulator, config)
-
-# Reset environment
-obs, info = env.reset()
-
-# Game loop
-for step in range(10000):
-    # Your policy computes actions for all agents
-    actions = policy.get_actions(obs)  # Dict[agent_id, action]
-
-    # Step environment
-    obs, rewards, terminated, truncated, info = env.step(actions)
-
-    if terminated or truncated:
-        obs, info = env.reset()
-```
-
-### `cogames run -m [MISSION] [-m MISSION...] -p POLICY [-p POLICY...]`
-
-Evaluate one or more policies on one or more missions.
-
-We provide a set of eval missions which you can use instead of missions `-m`. Specify `-S` or `--mission-set` among:
-`eval_missions`, `integrated_evals`, `spanning_evals`, `diagnostic_evals`, `all`.
-
-You can provide multiple `-p POLICY` arguments if you want to run evaluations on mixed-policy populations.
-
-**Examples:**
-
-```bash
-# Evaluate a checkpoint bundle
-cogames run -m machina_1 -p ./train_dir/my_run:v5
-
-# Evaluate across a mission set
-cogames run -S integrated_evals -p ./train_dir/my_run:v5
-
-# Mix two policies: 3 parts your policy, 5 parts random
-cogames run -m machina_1 -p ./train_dir/my_run:v5,proportion=3 -p class=random,proportion=5
-```
-
-**Options:**
-
-- `--episodes N`: Number of episodes per mission (default: 10)
-- `--action-timeout-ms N`: Timeout per action (default: 250ms)
-- `--steps N`: Max steps per episode
-- `--format [json/yaml]`: Output results as structured json or yaml (default: None for human-readable tables)
-
-When multiple policies are provided, `cogames run` fixes the number of agents each policy will control, but randomizes
-their assignments each episode.
-
-### `cogames make-mission -m [BASE_MISSION]`
-
-Create a custom mission configuration. In this case, the mission provided is the template mission to which you'll apply
-modifications.
-
-**Options:**
-
-- `--cogs N` or `-c N`: Number of cogs
-- `--width W` or `-w W`: Map width
-- `--height H` or `-h H`: Map height
-- `--output PATH`: Save to file
-
-Note: If `--cogs`, `--width`, or `--height` are not specified, the values come from the base mission's configuration.
-
-You will be able to provide your specified `--output` path as the `MISSION` argument to other `cogames` commands.
-
-## Policy Submission
-
-### `cogames login`
-
-Authenticate before uploading policies or viewing leaderboards.
-
-### `cogames upload -p [POLICY] -n [NAME]`
-
-Upload a policy to the server.
-
-```
-cogames submit -p ./train_dir/my_run:v5 -n my_policy
-```
-
-**Options:**
-
-- `--include-files`: Additional files to include (can be specified multiple times)
-- `--dry-run`: Validate the policy without uploading
-
-### `cogames seasons`
-
-List available tournament seasons you can submit to.
-
-### `cogames submit [POLICY] --season [SEASON]`
-
-Submit an uploaded policy to a tournament season.
-
-```bash
-# Submit latest version of a policy
-cogames submit my_policy --season alb-season-1
-
-# Submit a specific version
-cogames submit my_policy:v3 --season alb-season-1
-```
-
-### `cogames submissions`
-
-View your tournament submissions.
-
-```bash
-# View all submissions
-cogames submissions
-
-# Filter by season
-cogames submissions --season alb-season-1
-
-# Filter by policy (positional argument)
-cogames submissions my_policy
-```
-
-### `cogames leaderboard --season [SEASON]`
-
-View the leaderboard for a tournament season.
-
-```bash
-cogames leaderboard --season alb-season-1
-```
-
-When a policy is submitted to a season, it is queued for matches against other policies in that season's pools.
-
-## Citation
-
-If you use CoGames in your research, please cite:
-
-```bibtex
-@software{cogames2025,
-  title={CoGames: Multi-Agent Cooperative Game Environments},
-  author={Metta AI},
-  year={2025},
-  url={https://github.com/metta-ai/metta}
-}
-```

cogames-0.3.49.dist-info/RECORD

@@ -1,136 +0,0 @@
-cogames/__init__.py,sha256=Loao4kW7AqCRVKcQuA7lKEsyKl9k_Zf1oVlPXvgqjbw,23
-cogames/auth.py,sha256=W7BgRhrCTKob68p6HHTKVFjPayySaBG03eIgcGjw_jI,15852
-cogames/curricula.py,sha256=a7Nd-av4epAjmoqlefyU4q5eAitpYjCEGDCF_tS_iaY,825
-cogames/device.py,sha256=W8jfBxEZSbYVPyCNI5Ekze4dAL2uN6q48kgnY6iwIJg,1197
-cogames/evaluate.py,sha256=8pnSaReR-RLcoRob7Yxq9MlQjM3ahg8IYWWEBsoM21w,9760
-cogames/game.py,sha256=Qpyd4UOv97S-PCcEb422XFVbuXk46qhEx7_FlAr8ayA,3331
-cogames/main.py,sha256=crigZBTofYkemzgl25K1nKmt5xeowyhGE39uOq0kutM,44387
-cogames/play.py,sha256=7NyhqzwlaznRWHreOD_Z3vCjYYr1414usmNpkhNjsXg,2908
-cogames/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cogames/train.py,sha256=WLFlPgSem-OM5wDd9kMSrcG36cM8WADa-QNUrqnAyMI,16461
-cogames/verbose.py,sha256=f1pgjOcFev9GEGeXEUJBms8aN23HGepRxwGQHzxjQIA,2910
-cogames/cli/base.py,sha256=UpMqeJ0C8i0pkue1AHnnyyX0bFJ9zZeJ7HBR6yhuA8A,54
-cogames/cli/client.py,sha256=VqTmLH2tIspm9F6Q-IMqbbsBfmv0ZH3KSpDKSVYz_7I,7139
-cogames/cli/leaderboard.py,sha256=1M-XEkI2Z4JIMgkHgJGug90TqUwzXQnEbNeetPY50PY,11178
-cogames/cli/login.py,sha256=_i1Hdbp_wAMsX0NLbCTSr7GmOFbzSqwyNP79OqLOg40,1237
-cogames/cli/mission.py,sha256=7ElXtz6xhsgJ7NY6hYawAcNtzyXZ0rI9qeJVTqvpxkY,21485
-cogames/cli/policy.py,sha256=2kjZJm-TVp4rh697DHC6Mm0HrFUq6r7cDAOcL4D102A,7274
-cogames/cli/submit.py,sha256=4sJgk1_fASEPHBGPSyxr7GsjlI8A6sNBI9lb2SPgNbU,13850
-cogames/cli/utils.py,sha256=K4eb-RL73HtavNGxZjn_SVDLAwfFamLCEQNTCNVdmPU,895
-cogames/cogs_vs_clips/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-cogames/cogs_vs_clips/cogs_vs_clips_mapgen.md,sha256=zkVh30-tt0PZV6wsZy9RYZDTu1XNpaQ5eeEsFPlLWaE,13192
-cogames/cogs_vs_clips/mission.py,sha256=RBVcnZA6-WqTJTGM08_UBghLnK1AMVphPpfTD4QN0Cs,11990
-cogames/cogs_vs_clips/mission_utils.py,sha256=-tB8JclTaq8Zfh8V5DPor1A3Ncuq8ndsTjgVnIxUV7s,671
-cogames/cogs_vs_clips/missions.py,sha256=mil4s8PJ-khoIIQ_rKyQVLbb6qtyeJ58UvqBZm6gICs,5375
-cogames/cogs_vs_clips/procedural.py,sha256=tX7EFPmZDMU7axes8J_IuIPpR1kGXQBb2s7hkVgzP7g,25947
-cogames/cogs_vs_clips/sites.py,sha256=x7k-Xyn5fnn0m6o5YVkiGl2UxPwp2eT7ZhdrnhMa0pc,1960
-cogames/cogs_vs_clips/stations.py,sha256=SA8VcFuuYTWxxznvNS3sy-jHhpF8rtoy8JbcqiWvVPU,9122
-cogames/cogs_vs_clips/tutorial_missions.py,sha256=OgFi8yPmcmkZPmQFwUOi8D_fu4WlMUmLcdLr26ToOfk,715
-cogames/cogs_vs_clips/variants.py,sha256=ZxxC2hb5hj83W81Vm20HzdNiQx8xzOupsyjvTm3447I,29453
-cogames/cogs_vs_clips/evals/README.md,sha256=edBIBTd8Bi9b5YJaz_cUcX5s2-GxUc2ldVFnUzvsSpE,7289
-cogames/cogs_vs_clips/evals/diagnostic_evals.py,sha256=czQlTkgJHZvKhsdY2sTA566JF22bogtxozBd7iBlk6c,32052
-cogames/cogs_vs_clips/evals/difficulty_variants.py,sha256=QTzKC2PjbJczTAhd_uiYzIsdvyKbI69XJhar82n1RCM,17117
-cogames/cogs_vs_clips/evals/integrated_evals.py,sha256=pZamfnntHmtUK8c0V8aIDPhon7e2FN9DWvU9FmNB0Jc,4326
-cogames/cogs_vs_clips/evals/spanning_evals.py,sha256=rY6gSX8_-ROb8p007_3PUt5FQBNSSbuce-YDIi7mf10,12943
-cogames/maps/canidate1_1000.map,sha256=_Gj_pZM901N0OKeGCet2MDuHKMFdKp-7HkUseZat-JE,1023279
-cogames/maps/canidate1_1000_stations.map,sha256=JozyCXgJGzf73QaFGFh80AU2Xgp-Lb0yPN7LsExttyo,1023407
-cogames/maps/canidate1_500.map,sha256=J0arXU-AcWxTVV4Iy6T5d8-zij-WeoGxDyBIxwfbt2Y,261779
-cogames/maps/canidate1_500_stations.map,sha256=TTBLUglegJq_9lzR1a3DQRetMXuL3xRKw3dldsKLk-Q,261907
-cogames/maps/canidate2_1000.map,sha256=52Ioj0aLRNg0MFXbAPdOh9o9sL8oHN1oKK-QCy5r0u4,1023279
-cogames/maps/canidate2_1000_stations.map,sha256=Oy3I5qpZoUin9nrvOlk4yn4qwtMLqorF5QnedBZUW_U,1023407
-cogames/maps/canidate2_500.map,sha256=5s4T6wg6rlXNTu84Nr2CA_RlErvPCjTxzEzPlTpnfNI,261779
-cogames/maps/canidate2_500_stations.map,sha256=AFN3PrBrizgLzAtrZwlcBGt6_27AZ56rOJzAbCGb8Zg,261894
-cogames/maps/canidate3_1000.map,sha256=SNnIbpFBxk-EirpEBIuX44c_KJICiBPylGEE0QGP23A,1023279
-cogames/maps/canidate3_1000_stations.map,sha256=gc7F3oQkwgWgfHPWtlUNuVgqh07FX2OLFI_ne32qZ7M,1023407
-cogames/maps/canidate3_500.map,sha256=mEJ89RgtAMZiiTK0DWTZdxdbRpq9A_zNXA9aK3hAAj8,261779
-cogames/maps/canidate3_500_stations.map,sha256=xJqbr_xD_WVqQaD8leEv5R9oQE5lm9m9eI2QuG2IBoo,261907
-cogames/maps/canidate4_500.map,sha256=d7XErhvS4AQ6g2In2BHo4JidkOxFcOZbPXIQ9Lq_7q0,261779
-cogames/maps/canidate4_500_stations.map,sha256=iblHYTDrtVlWvfq6c1e2OCaNNnzcM8BcxjOdaH7TIDQ,261907
-cogames/maps/cave_base_50.map,sha256=IpNeXE3c42CpVatlpm5a4uNPe5qUoPFxqeJV3DjS954,4057
-cogames/maps/machina_100_stations.map,sha256=XgVJeKkJSRc6B3B6uCu1f-CIMIgbk2m6DkltMxP92-I,12707
-cogames/maps/machina_200_stations.map,sha256=-0ngnGzYyVRLSO-ltXrAPOtDVM6FLuqEeapCWMHjDzc,45007
-cogames/maps/machina_200_stations_small.map,sha256=3ZY33TCbrWllP201sJbp4cw0dc51sO52-lNjL3ClPpA,5932
-cogames/maps/machina_eval_exp01.map,sha256=6Szry8uNbfZxLpm8oZaeYGRyjbp2_ahyUVQd4rv6KR4,2078
-cogames/maps/machina_eval_template_large.map,sha256=1aCZT_9E45czViWjuxHspVDKurAsDr0_txGbGvnB1JA,4828
-cogames/maps/machinatrainer4agents.map,sha256=FA8oOHpalRtCRrAweV7lBWZ5x7-KsTJ4HRkIIeiXsKI,5387
-cogames/maps/machinatrainer4agentsbase.map,sha256=DLNy4UbFnjNjoD-NFIwRjV6H9sMH8evz8BeobPXgwfs,5387
-cogames/maps/machinatrainerbig.map,sha256=xX_x-c8kVyQ7Q4c1wQXialxUozdeZIWMNDX3QRJdIT4,51353
-cogames/maps/machinatrainersmall.map,sha256=H7pJ8uaEa-DZ3RcaLoiY3_GjDxZzz0w_jrlkOq0XFDc,12481
-cogames/maps/training_facility_clipped.map,sha256=lmuigg0KlxJ1jfQika-E99fjQ6RbPIuYsXVh7Lo7ATo,1363
-cogames/maps/training_facility_open_1.map,sha256=2sPq0bjtizTYsKjgkl2WuKxfK1HjFCrEUc--RwpvHTY,781
-cogames/maps/training_facility_open_2.map,sha256=J2U0uIiqv08YxDI4SUzOuRry3ipiUu6MupshfNgPazQ,1331
-cogames/maps/training_facility_open_3.map,sha256=xvNWJcjDFME-roiDFwS1D3xfm7SWGC2jKVoxZnT5yQg,781
-cogames/maps/training_facility_tight_4.map,sha256=hDUlydjle0CbMdHdXzepmRRBqYWxTyycVPs8O-ovi18,781
-cogames/maps/training_facility_tight_5.map,sha256=gs1mj6FKdUphkG1Z8WmBKJK0HJh4uyxZE6x31nqdT4s,781
-cogames/maps/vanilla_large.map,sha256=fX9s0zxL3nhaaikWryjcqyZdjhVQX4k4u_6rSJsHvQ8,2067
-cogames/maps/vanilla_small.map,sha256=U6pHaUf87EJJcswUkZdn1m2xznf4PQYYNhfvcXN89VU,595
-cogames/maps/zelda.map,sha256=1_rwezA27n5V9R3JY7WXniFVm8d31_Y1kyr9vn_gPjg,22387
-cogames/maps/diagnostic_evals/diagnostic_agile.map,sha256=dO_XkAZ272HcgEHfgKtaY8R-zvhxZ26MGkgWSQ7MtfU,817
-cogames/maps/diagnostic_evals/diagnostic_agile_hard.map,sha256=4odtqRuQj5CFIy_yIvu4VOxyqWC9J3lyGGIXbDkrfmw,1545
-cogames/maps/diagnostic_evals/diagnostic_assembler_near.map,sha256=xjwwBJ7BKzZEJat8by2tslwzlxvhA3tDZZfZKd2jVws,1801
-cogames/maps/diagnostic_evals/diagnostic_assembler_search.map,sha256=O2Osm8FT0mBepEZByaqueWmEpcpJqDA9AkmekELb50E,1801
-cogames/maps/diagnostic_evals/diagnostic_assembler_search_hard.map,sha256=ICJ730O2G9q_0e9AN_ODEnFFr729d7UfKK0X4mQEmIU,3557
-cogames/maps/diagnostic_evals/diagnostic_charge_up.map,sha256=0CXZLEgo1wQBqetHhT0MX782Q1xKSzFHfi4ZFzLLAYU,836
-cogames/maps/diagnostic_evals/diagnostic_charge_up_hard.map,sha256=CTkIsn_4CoOD8G_NnDUJsj8r3OdiYCXndPQfG9EDL00,1706
-cogames/maps/diagnostic_evals/diagnostic_chest_navigation1.map,sha256=_-4ZM4gVcFZ3rU5hXnGE9zGU-ykfx1PPFnS2EFifRco,1768
-cogames/maps/diagnostic_evals/diagnostic_chest_navigation1_hard.map,sha256=Q0NDvy0nXyK3-TKP5FYsEGVpoRAwZt7_cfP0VH5XbrI,3101
-cogames/maps/diagnostic_evals/diagnostic_chest_navigation2.map,sha256=fMrCH5NYcKzJNkdxmyi9QaJcnW98j7J3vFm4-hsuT94,1046
-cogames/maps/diagnostic_evals/diagnostic_chest_navigation2_hard.map,sha256=7yaefN8WFEya9thywWXCS0nWsZEn3WLP_OFpmmILyi8,2775
-cogames/maps/diagnostic_evals/diagnostic_chest_navigation3.map,sha256=tYtF-xZgzQ3JRtUT3-JKJGRXqzrl8XoN7p4A2Z9yg_0,1128
-cogames/maps/diagnostic_evals/diagnostic_chest_navigation3_hard.map,sha256=u5FvEItCfIIjtrdX0PjN7E3aMkyGmplrdXSBUfn1wzg,2641
-cogames/maps/diagnostic_evals/diagnostic_chest_near.map,sha256=UZYegZBpeBt8-vVhxcarXpYazZAU244lbYfWggnKVGw,1803
-cogames/maps/diagnostic_evals/diagnostic_chest_search.map,sha256=UFHhWbD2NqiJmR_rNSFJyskfpTbnLaqx24QBIln5auo,1803
-cogames/maps/diagnostic_evals/diagnostic_chest_search_hard.map,sha256=EZlrxKqBbmGeE6AWmyrK2nhINUNnHpFD2m_zoir1U9o,14383
-cogames/maps/diagnostic_evals/diagnostic_extract_lab.map,sha256=va2SPYE0_VhxwqNfoOFIeGgr_IlSKkLl8d20MQM0r1Q,647
-cogames/maps/diagnostic_evals/diagnostic_extract_lab_hard.map,sha256=idMpcrIPEOTaAmgh2hObqcylW4IT3P1UybPh7IgU0UA,1517
-cogames/maps/diagnostic_evals/diagnostic_memory.map,sha256=tQNZUp5zTfwbV0G2h_v_Gq70wcFEHUOXXCDbjXFPV6w,1215
-cogames/maps/diagnostic_evals/diagnostic_memory_hard.map,sha256=3b-KAx4aJLIquxv7oYNib3IhkNYVep_mgdmNx1VJGds,1997
-cogames/maps/diagnostic_evals/diagnostic_radial.map,sha256=vVTVC1EpGx-e1w11qmzHtjH_arug8Uih0x8vleoDzh8,3050
-cogames/maps/diagnostic_evals/diagnostic_radial_hard.map,sha256=9Cd47JyBZwfIXjZyiptny95EsEYAU-t2PEeaIjJ5TqQ,24530
-cogames/maps/diagnostic_evals/diagnostic_resource_lab.map,sha256=Sqk-bkc9OhTZe-HIIg6-H3Z7SFTzaOdaHj5YrDai_w8,1803
-cogames/maps/diagnostic_evals/diagnostic_unclip.map,sha256=R2c3m6_ZmhOFEW61mcOCHaS-svhLAHVk7zv9J02gUaM,1803
-cogames/maps/evals/eval_balanced_spread.map,sha256=-0tMpq_25Fsv3Xtpn72jtTMel1yiHMutv4nzac0JjGI,2077
-cogames/maps/evals/eval_clip_oxygen.map,sha256=sy-Ry3L5My-ZH01Qj4_v44ptyAgG61f3uOfHl1ntVFA,2079
-cogames/maps/evals/eval_collect_resources.map,sha256=ytd3twE-kji3DaRHvaSWrwR_XsJFEETEUhZUotwVck4,2079
-cogames/maps/evals/eval_collect_resources_hard.map,sha256=MaM-B3l1jlSDdhlMTGT8rr49BO_eKC3WLanpdsMBdcg,2079
-cogames/maps/evals/eval_collect_resources_medium.map,sha256=H5FnKribLt6N-IfwdhF8DXN0uuIYmV6AVQ2TrlHOe6Q,2079
-cogames/maps/evals/eval_divide_and_conquer.map,sha256=JRt5GhtOOTVsY8Zo7HVmuQ-GXuiye1SNeXI7fO71WaY,2077
-cogames/maps/evals/eval_energy_starved.map,sha256=h5j0uX-Z56PeSwbYMWPAyup0CU6OQSKRskxoj3BmoOs,2077
-cogames/maps/evals/eval_multi_coordinated_collect_hard.map,sha256=CcwfvDInnj5yZd24wwFSOcE5l4IrCifIGhZ3BK-2V5o,2080
-cogames/maps/evals/eval_oxygen_bottleneck.map,sha256=OS1wzZvcxSCBLmaNjk3A2Wo-1rz-G841C-3rH4-i21A,2079
-cogames/maps/evals/eval_single_use_world.map,sha256=0oAQsFfwlA7T4Ate8nfyRTnL87YZ0FHEGHjPb_WzSUQ,2079
-cogames/maps/evals/extractor_hub_100x100.map,sha256=IQACKX6pzWsXntqBprwcVnA2wE0jaFeIxGoWum0M7g0,12707
-cogames/maps/evals/extractor_hub_30x30.map,sha256=UWkoSqemrFPpOsAbHaHbA9vGgXhIXhmovF5s2xKHezQ,1997
-cogames/maps/evals/extractor_hub_50x50.map,sha256=SH4lA8DkUrN1q6Ftfe9UTyQSVsmULyX5NqLAyd_J8x8,4057
-cogames/maps/evals/extractor_hub_70x70.map,sha256=8a7KO_qJF3M15D_GWuB04wIdAXzMiZdYBDC20DlCd6M,6917
-cogames/maps/evals/extractor_hub_80x80.map,sha256=rql-jda3jLTL3uHo2Mx2tM5rP5RqA-3H7GP45tFc0zI,8647
-cogames/policy/__init__.py,sha256=JFjmvqYzj_j_mQ4Bmqmc60KU49HF63i0s8lIEu1G_b4,116
-cogames/policy/pufferlib_policy.py,sha256=o7si3aHKQz2cTQfn7UvF_uQhVmoOWNbRVf8wtZLCxJE,4211
-cogames/policy/signal_handler.py,sha256=19_i72AlYZmMifBDvZuaqLVrFIbWLa8mW-7In7nbG3c,2060
-cogames/policy/trainable_policy_template.py,sha256=49RGfXBQON04Y6Pg56xHKKkO446a3BtMyaS-brrFMJY,7168
-cogames/policy/nim_agents/__init__.py,sha256=sKbQiAKI4lQOVJ1knC0r4iwicrUOmfK6RVzMSV-oDP4,474
-cogames/policy/nim_agents/agents.py,sha256=rtT6qITV6slrffH6ci3GPb2Rpe_Qd1pMvrtQOOzPsEw,1851
-cogames/policy/nim_agents/common.nim,sha256=QGb1EcyBb5tO3OTfILaJ_o65doGUI-W4wzfwU5ENcH8,26990
-cogames/policy/nim_agents/install.sh,sha256=mI-0Er8Figfd2InUntU3ECw0S3RM_ucOaAHIA2iwacc,21
-cogames/policy/nim_agents/ladybug_agent.nim,sha256=pVrvSDX6uazI8HsI6-3br88gKkvihstdseYAouHWVRs,36274
-cogames/policy/nim_agents/nim_agents.nim,sha256=QmWWK53ZkNzzkD4mKF2obAabgmrOVKQYpXAg6M9NjY4,1280
-cogames/policy/nim_agents/nim_agents.nims,sha256=_kmsdrq3CdFlGiKSn6puinVSLBUVx8dAQPabi1Ujf-4,317
-cogames/policy/nim_agents/nimby.lock,sha256=avC4D_2bYFgguUlGWXUm_zvgk8PeQjk2NYY0wN0xdM8,265
-cogames/policy/nim_agents/racecar_agents.nim,sha256=0ce_xWh4spigaNK33sLjCozXIc6Mg-QbeHHy1jQvG4E,35145
-cogames/policy/nim_agents/random_agents.nim,sha256=LCggSOdwWJDsg9corkmJVPUhPK2bscVJJrREyV2ChJw,1867
-cogames/policy/nim_agents/test_agents.py,sha256=XCrefvJEIhJBgCRcrBK1xJSZkGuTcyiNMUVwIwP9aBE,1290
-cogames/policy/nim_agents/thinky_agents.nim,sha256=pOS3gs4N0YwySn9ertUVYkpVtpobQnLWNflbzeVtyU8,27281
-cogames/policy/nim_agents/thinky_eval.py,sha256=wqe0y8tAAMtgVdY1GPGucFTjlMUAgkb6FtBN72Ve6hM,8991
-cogames/policy/scripted_agent/README.md,sha256=o7i7BDcc6zrtbj0WenGvjaX6iLs08bkWaqWUPp1801s,9836
-cogames/policy/scripted_agent/baseline_agent.py,sha256=Plq8Br5vCxFUaLLc_6k-vSLG1YlagS1nH-gi4JO7MfQ,43598
-cogames/policy/scripted_agent/demo_policy.py,sha256=IjyfktwANe_2vlvrDjMwEXwmk2Y3Tb-VQ37xtLpi2Zk,9533
-cogames/policy/scripted_agent/pathfinding.py,sha256=E6BhwtCeZdePadA9-pQBjWYr5AMEh4zahmRfENx12uo,3936
-cogames/policy/scripted_agent/starter_agent.py,sha256=BLkydr2H_PD0mSLfzHuxbZXfc8JkeN17B1EaltFXaQg,6200
-cogames/policy/scripted_agent/types.py,sha256=6UaYXNejiTlhd7F1Z_YXQZowxKUOk9NKySAkgXlM78Q,8185
-cogames/policy/scripted_agent/unclipping_agent.py,sha256=bB-wGVQ1pcl23y69gj3KGF3UMCiZ5kvdfGJ8hUPJ0DA,20108
-cogames/policy/scripted_agent/utils.py,sha256=mdWZJn7wkt4AlE-nGfK4dqrsSF_sU99wwOuFGnVC9H8,13347
-cogames-0.3.49.dist-info/METADATA,sha256=xqnsUvgVzEAqzWiiQs53PD73mj1YRGmjWogv7t5_38U,14085
-cogames-0.3.49.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-cogames-0.3.49.dist-info/entry_points.txt,sha256=GTHdgj-RC2hQYmjUMSp9RHX8kbru19k0LS2lAj8DnLE,45
-cogames-0.3.49.dist-info/top_level.txt,sha256=Wzwo0qj8ePPKwqQ0dPbpH2W5ZK40npYCzoTQ-nefqtM,8
-cogames-0.3.49.dist-info/RECORD,,

cogames-0.3.49.dist-info/top_level.txt

@@ -1 +0,0 @@
-cogames