tuff-rl 0.1.0__tar.gz

tuff_rl-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Talex-Touch contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

tuff_rl-0.1.0/MANIFEST.in

@@ -0,0 +1,2 @@
+graft tests
+global-exclude __pycache__ *.py[cod]

tuff_rl-0.1.0/PKG-INFO

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: tuff-rl
+Version: 0.1.0
+Summary: Training logs as TensorBoard event files, and a live board that follows them
+Author: TalexDreamSoul
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/talex-touch/tuff-rl
+Project-URL: Repository, https://github.com/talex-touch/tuff-rl
+Project-URL: Issues, https://github.com/talex-touch/tuff-rl/issues
+Project-URL: Changelog, https://github.com/talex-touch/tuff-rl/blob/main/CHANGELOG.md
+Keywords: reinforcement-learning,tensorboard,tfevents,experiment-tracking,training-dashboard,machine-learning
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Web Environment
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: system
+Requires-Dist: psutil>=5.9; extra == "system"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: tensorboard>=2.15; extra == "dev"
+Requires-Dist: tensorboardX>=2.6; extra == "dev"
+Dynamic: license-file
+
+# tuff-rl
+
+**Training logs as TensorBoard event files, and a live board that follows them.**
+
+[English](https://github.com/talex-touch/tuff-rl/blob/main/README.md) · [简体中文](https://github.com/talex-touch/tuff-rl/blob/main/README.zh.md)
+
+[![PyPI](https://img.shields.io/pypi/v/tuff-rl)](https://pypi.org/project/tuff-rl/)
+[![Python](https://img.shields.io/pypi/pyversions/tuff-rl)](https://pypi.org/project/tuff-rl/)
+[![CI](https://github.com/talex-touch/tuff-rl/actions/workflows/ci.yml/badge.svg)](https://github.com/talex-touch/tuff-rl/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue)](https://github.com/talex-touch/tuff-rl/blob/main/LICENSE)
+
+![The board following six CartPole runs while they train](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-live.gif)
+
+One call in a training script writes everything about the run into TensorBoard event files
+under `logs/`: the metrics, the config, what the script prints, and the CPU, memory and GPU
+it used. The same call starts a board in your browser that follows those files as they grow.
+`tensorboard --logdir logs` opens the same files, and the board opens directories that
+TensorBoard, tensorboardX or PyTorch wrote. The package has no dependencies.
+
+## Install
+
+```bash
+pip install tuff-rl
+pip install "tuff-rl[system]"   # adds CPU and memory metrics, through psutil
+```
+
+## Quick start
+
+```python
+import tuffrl
+
+run = tuffrl.init(logdir="logs", group="cartpole/lr-0.5", name="seed-0", config={"lr": 0.5, "gamma": 0.99})
+for step in range(10_000):
+    ...
+    run.log({"train": {"loss": loss, "return": episode_return}}, step=step)
+run.finish()
+```
+
+The first script to start opens the board at <http://127.0.0.1:6066>; scripts started later
+join it, so a sweep of many processes shares one board. A run that ends with an exception is
+marked failed, and one stopped with Ctrl-C is marked stopped. Under `torch.distributed`, only
+rank 0 starts the board.
+
+Code that already uses PyTorch's `SummaryWriter` changes only its import:
+
+```python
+from tuffrl import SummaryWriter
+```
+
+The shim covers `add_scalar`, `add_scalars`, `add_text`, `add_hparams`, `flush` and `close`.
+
+## Try the demo
+
+```bash
+pip install "tuff-rl[system]"
+curl -O https://raw.githubusercontent.com/talex-touch/tuff-rl/main/examples/cartpole.py
+python cartpole.py
+```
+
+REINFORCE on CartPole in plain Python: two learning rates, three seeds each, six processes
+in parallel. It takes about 35 seconds.
+
+## The board
+
+| | |
+| --- | --- |
+| ![Two learning rates, each drawn as the mean of three seeds with a band for their spread](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-groups.png) | ![The config of six runs side by side, with the two differing keys marked](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-config.png) |
+| Runs in one directory form a group. Merged, a group is drawn as its mean with a band for the spread of its runs. | The config of every run side by side, with the keys that differ marked. |
+| ![The printed output of one run, with stderr in red](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-output.png) | ![CPU and memory charts for the runs](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-system.png) |
+| What each run printed, stdout and stderr in order, searchable, following new lines. | CPU and memory of the training machine and process, and the GPUs that `nvidia-smi` reports. |
+
+Charts smooth with an exponential moving average and can also show the raw values and a log
+x-axis. Drag across a chart to zoom in, and double-click it to zoom back out. The board
+follows the system's light or dark theme.
+
+## Training on another machine
+
+Over SSH the board starts on the training machine and does not open a browser. Instead it
+prints the command that forwards its port to your own machine:
+
+```text
+[tuffrl] board: http://127.0.0.1:6066  (logdir /data/logs)
+[tuffrl] from your own machine: ssh -N -L 6066:127.0.0.1:6066 you@gpu-box  then open http://127.0.0.1:6066
+```
+
+The board has no login. It listens on 127.0.0.1 unless `TUFFRL_BOARD_HOST` says otherwise;
+listening on another address shows your logs and config to anyone who can reach that port.
+
+## Command line and settings
+
+```bash
+tuff-rl board logs   # serve a log directory, including one TensorBoard wrote
+tuff-rl stop logs    # stop the board serving it
+```
+
+| Variable | Effect |
+| --- | --- |
+| `TUFFRL_BOARD=0` | Training scripts do not start the board. |
+| `TUFFRL_OPEN_BROWSER=0` | The board starts but no browser opens. |
+| `TUFFRL_BOARD_PORT` | Port to try first (default 6066); the next free one is used when it is taken. |
+| `TUFFRL_BOARD_HOST` | Address to listen on (default 127.0.0.1). |
+
+## How it works
+
+- **Event files.** The writer frames records the way TFRecord does (length, CRC32C, data,
+  CRC32C) and encodes the `Event` and `Summary` protobufs by hand, so neither TensorFlow nor
+  protobuf is needed. Metrics are scalar summaries, printed output uses the text plugin, and
+  the config is an HParams session, so TensorBoard's HParams tab lists the runs and groups
+  them by `group`.
+- **The board.** A standard-library HTTP server reads each event file from where it stopped,
+  and the page receives a snapshot followed by a stream of new points (server-sent events).
+  The page is a Vue app built on [TuffEx](https://www.npmjs.com/package/@talex-touch/tuffex)
+  and ships inside the wheel.
+- **One board per log directory.** `logs/.tuffrl/board.json` records which board serves the
+  directory. Scripts starting at the same moment agree on one of them to launch it, and the
+  board keeps running after training ends until `tuff-rl stop`.
+
+## Status
+
+0.1 is an alpha. The board reads images and audio but does not show them yet; that and the
+rest of the plan are in the [roadmap issues](https://github.com/talex-touch/tuff-rl/issues?q=is%3Aissue+label%3Aroadmap).
+
+## Development
+
+```bash
+cd web && pnpm install && pnpm build && cd ..   # builds the board page into src/tuffrl/board/static
+pip install -e ".[dev,system]"
+python -m pytest
+uvx ruff check .
+```
+
+See [CONTRIBUTING.md](https://github.com/talex-touch/tuff-rl/blob/main/CONTRIBUTING.md) for the rest, including how a release is made.
+
+## License
+
+[MIT](https://github.com/talex-touch/tuff-rl/blob/main/LICENSE)

tuff_rl-0.1.0/README.md

@@ -0,0 +1,136 @@
+# tuff-rl
+
+**Training logs as TensorBoard event files, and a live board that follows them.**
+
+[English](https://github.com/talex-touch/tuff-rl/blob/main/README.md) · [简体中文](https://github.com/talex-touch/tuff-rl/blob/main/README.zh.md)
+
+[![PyPI](https://img.shields.io/pypi/v/tuff-rl)](https://pypi.org/project/tuff-rl/)
+[![Python](https://img.shields.io/pypi/pyversions/tuff-rl)](https://pypi.org/project/tuff-rl/)
+[![CI](https://github.com/talex-touch/tuff-rl/actions/workflows/ci.yml/badge.svg)](https://github.com/talex-touch/tuff-rl/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue)](https://github.com/talex-touch/tuff-rl/blob/main/LICENSE)
+
+![The board following six CartPole runs while they train](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-live.gif)
+
+One call in a training script writes everything about the run into TensorBoard event files
+under `logs/`: the metrics, the config, what the script prints, and the CPU, memory and GPU
+it used. The same call starts a board in your browser that follows those files as they grow.
+`tensorboard --logdir logs` opens the same files, and the board opens directories that
+TensorBoard, tensorboardX or PyTorch wrote. The package has no dependencies.
+
+## Install
+
+```bash
+pip install tuff-rl
+pip install "tuff-rl[system]"   # adds CPU and memory metrics, through psutil
+```
+
+## Quick start
+
+```python
+import tuffrl
+
+run = tuffrl.init(logdir="logs", group="cartpole/lr-0.5", name="seed-0", config={"lr": 0.5, "gamma": 0.99})
+for step in range(10_000):
+    ...
+    run.log({"train": {"loss": loss, "return": episode_return}}, step=step)
+run.finish()
+```
+
+The first script to start opens the board at <http://127.0.0.1:6066>; scripts started later
+join it, so a sweep of many processes shares one board. A run that ends with an exception is
+marked failed, and one stopped with Ctrl-C is marked stopped. Under `torch.distributed`, only
+rank 0 starts the board.
+
+Code that already uses PyTorch's `SummaryWriter` changes only its import:
+
+```python
+from tuffrl import SummaryWriter
+```
+
+The shim covers `add_scalar`, `add_scalars`, `add_text`, `add_hparams`, `flush` and `close`.
+
+## Try the demo
+
+```bash
+pip install "tuff-rl[system]"
+curl -O https://raw.githubusercontent.com/talex-touch/tuff-rl/main/examples/cartpole.py
+python cartpole.py
+```
+
+REINFORCE on CartPole in plain Python: two learning rates, three seeds each, six processes
+in parallel. It takes about 35 seconds.
+
+## The board
+
+| | |
+| --- | --- |
+| ![Two learning rates, each drawn as the mean of three seeds with a band for their spread](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-groups.png) | ![The config of six runs side by side, with the two differing keys marked](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-config.png) |
+| Runs in one directory form a group. Merged, a group is drawn as its mean with a band for the spread of its runs. | The config of every run side by side, with the keys that differ marked. |
+| ![The printed output of one run, with stderr in red](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-output.png) | ![CPU and memory charts for the runs](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-system.png) |
+| What each run printed, stdout and stderr in order, searchable, following new lines. | CPU and memory of the training machine and process, and the GPUs that `nvidia-smi` reports. |
+
+Charts smooth with an exponential moving average and can also show the raw values and a log
+x-axis. Drag across a chart to zoom in, and double-click it to zoom back out. The board
+follows the system's light or dark theme.
+
+## Training on another machine
+
+Over SSH the board starts on the training machine and does not open a browser. Instead it
+prints the command that forwards its port to your own machine:
+
+```text
+[tuffrl] board: http://127.0.0.1:6066  (logdir /data/logs)
+[tuffrl] from your own machine: ssh -N -L 6066:127.0.0.1:6066 you@gpu-box  then open http://127.0.0.1:6066
+```
+
+The board has no login. It listens on 127.0.0.1 unless `TUFFRL_BOARD_HOST` says otherwise;
+listening on another address shows your logs and config to anyone who can reach that port.
+
+## Command line and settings
+
+```bash
+tuff-rl board logs   # serve a log directory, including one TensorBoard wrote
+tuff-rl stop logs    # stop the board serving it
+```
+
+| Variable | Effect |
+| --- | --- |
+| `TUFFRL_BOARD=0` | Training scripts do not start the board. |
+| `TUFFRL_OPEN_BROWSER=0` | The board starts but no browser opens. |
+| `TUFFRL_BOARD_PORT` | Port to try first (default 6066); the next free one is used when it is taken. |
+| `TUFFRL_BOARD_HOST` | Address to listen on (default 127.0.0.1). |
+
+## How it works
+
+- **Event files.** The writer frames records the way TFRecord does (length, CRC32C, data,
+  CRC32C) and encodes the `Event` and `Summary` protobufs by hand, so neither TensorFlow nor
+  protobuf is needed. Metrics are scalar summaries, printed output uses the text plugin, and
+  the config is an HParams session, so TensorBoard's HParams tab lists the runs and groups
+  them by `group`.
+- **The board.** A standard-library HTTP server reads each event file from where it stopped,
+  and the page receives a snapshot followed by a stream of new points (server-sent events).
+  The page is a Vue app built on [TuffEx](https://www.npmjs.com/package/@talex-touch/tuffex)
+  and ships inside the wheel.
+- **One board per log directory.** `logs/.tuffrl/board.json` records which board serves the
+  directory. Scripts starting at the same moment agree on one of them to launch it, and the
+  board keeps running after training ends until `tuff-rl stop`.
+
+## Status
+
+0.1 is an alpha. The board reads images and audio but does not show them yet; that and the
+rest of the plan are in the [roadmap issues](https://github.com/talex-touch/tuff-rl/issues?q=is%3Aissue+label%3Aroadmap).
+
+## Development
+
+```bash
+cd web && pnpm install && pnpm build && cd ..   # builds the board page into src/tuffrl/board/static
+pip install -e ".[dev,system]"
+python -m pytest
+uvx ruff check .
+```
+
+See [CONTRIBUTING.md](https://github.com/talex-touch/tuff-rl/blob/main/CONTRIBUTING.md) for the rest, including how a release is made.
+
+## License
+
+[MIT](https://github.com/talex-touch/tuff-rl/blob/main/LICENSE)

tuff_rl-0.1.0/pyproject.toml

@@ -0,0 +1,66 @@
+[build-system]
+requires = ["setuptools>=77"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tuff-rl"
+dynamic = ["version"]
+description = "Training logs as TensorBoard event files, and a live board that follows them"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [{ name = "TalexDreamSoul" }]
+keywords = ["reinforcement-learning", "tensorboard", "tfevents", "experiment-tracking", "training-dashboard", "machine-learning"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Environment :: Web Environment",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "Operating System :: MacOS",
+  "Operating System :: POSIX :: Linux",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+  "Topic :: Scientific/Engineering :: Visualization",
+]
+# The writer, the reader and the board run on the standard library alone, so the package
+# installs on any training machine without touching its environment.
+dependencies = []
+
+[project.urls]
+Homepage = "https://github.com/talex-touch/tuff-rl"
+Repository = "https://github.com/talex-touch/tuff-rl"
+Issues = "https://github.com/talex-touch/tuff-rl/issues"
+Changelog = "https://github.com/talex-touch/tuff-rl/blob/main/CHANGELOG.md"
+
+[project.optional-dependencies]
+# Process and machine metrics; without it the board records only what the standard library sees.
+system = ["psutil>=5.9"]
+dev = ["pytest>=8.0", "tensorboard>=2.15", "tensorboardX>=2.6"]
+
+[project.scripts]
+tuff-rl = "tuffrl.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+# Built from web/ (pnpm build) before packaging; the release workflow checks it is there.
+tuffrl = ["board/static/**/*"]
+
+[tool.setuptools.dynamic]
+version = { attr = "tuffrl.__version__" }
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 160
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E4", "E7", "E9", "F", "W", "I", "UP", "B", "SIM", "ARG", "A", "N", "BLE"]

tuff_rl-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

tuff_rl-0.1.0/src/tuff_rl.egg-info/PKG-INFO

@@ -0,0 +1,171 @@
+Metadata-Version: 2.4
+Name: tuff-rl
+Version: 0.1.0
+Summary: Training logs as TensorBoard event files, and a live board that follows them
+Author: TalexDreamSoul
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/talex-touch/tuff-rl
+Project-URL: Repository, https://github.com/talex-touch/tuff-rl
+Project-URL: Issues, https://github.com/talex-touch/tuff-rl/issues
+Project-URL: Changelog, https://github.com/talex-touch/tuff-rl/blob/main/CHANGELOG.md
+Keywords: reinforcement-learning,tensorboard,tfevents,experiment-tracking,training-dashboard,machine-learning
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Web Environment
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: system
+Requires-Dist: psutil>=5.9; extra == "system"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: tensorboard>=2.15; extra == "dev"
+Requires-Dist: tensorboardX>=2.6; extra == "dev"
+Dynamic: license-file
+
+# tuff-rl
+
+**Training logs as TensorBoard event files, and a live board that follows them.**
+
+[English](https://github.com/talex-touch/tuff-rl/blob/main/README.md) · [简体中文](https://github.com/talex-touch/tuff-rl/blob/main/README.zh.md)
+
+[![PyPI](https://img.shields.io/pypi/v/tuff-rl)](https://pypi.org/project/tuff-rl/)
+[![Python](https://img.shields.io/pypi/pyversions/tuff-rl)](https://pypi.org/project/tuff-rl/)
+[![CI](https://github.com/talex-touch/tuff-rl/actions/workflows/ci.yml/badge.svg)](https://github.com/talex-touch/tuff-rl/actions/workflows/ci.yml)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue)](https://github.com/talex-touch/tuff-rl/blob/main/LICENSE)
+
+![The board following six CartPole runs while they train](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-live.gif)
+
+One call in a training script writes everything about the run into TensorBoard event files
+under `logs/`: the metrics, the config, what the script prints, and the CPU, memory and GPU
+it used. The same call starts a board in your browser that follows those files as they grow.
+`tensorboard --logdir logs` opens the same files, and the board opens directories that
+TensorBoard, tensorboardX or PyTorch wrote. The package has no dependencies.
+
+## Install
+
+```bash
+pip install tuff-rl
+pip install "tuff-rl[system]"   # adds CPU and memory metrics, through psutil
+```
+
+## Quick start
+
+```python
+import tuffrl
+
+run = tuffrl.init(logdir="logs", group="cartpole/lr-0.5", name="seed-0", config={"lr": 0.5, "gamma": 0.99})
+for step in range(10_000):
+    ...
+    run.log({"train": {"loss": loss, "return": episode_return}}, step=step)
+run.finish()
+```
+
+The first script to start opens the board at <http://127.0.0.1:6066>; scripts started later
+join it, so a sweep of many processes shares one board. A run that ends with an exception is
+marked failed, and one stopped with Ctrl-C is marked stopped. Under `torch.distributed`, only
+rank 0 starts the board.
+
+Code that already uses PyTorch's `SummaryWriter` changes only its import:
+
+```python
+from tuffrl import SummaryWriter
+```
+
+The shim covers `add_scalar`, `add_scalars`, `add_text`, `add_hparams`, `flush` and `close`.
+
+## Try the demo
+
+```bash
+pip install "tuff-rl[system]"
+curl -O https://raw.githubusercontent.com/talex-touch/tuff-rl/main/examples/cartpole.py
+python cartpole.py
+```
+
+REINFORCE on CartPole in plain Python: two learning rates, three seeds each, six processes
+in parallel. It takes about 35 seconds.
+
+## The board
+
+| | |
+| --- | --- |
+| ![Two learning rates, each drawn as the mean of three seeds with a band for their spread](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-groups.png) | ![The config of six runs side by side, with the two differing keys marked](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-config.png) |
+| Runs in one directory form a group. Merged, a group is drawn as its mean with a band for the spread of its runs. | The config of every run side by side, with the keys that differ marked. |
+| ![The printed output of one run, with stderr in red](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-output.png) | ![CPU and memory charts for the runs](https://raw.githubusercontent.com/talex-touch/tuff-rl/main/docs/images/board-system.png) |
+| What each run printed, stdout and stderr in order, searchable, following new lines. | CPU and memory of the training machine and process, and the GPUs that `nvidia-smi` reports. |
+
+Charts smooth with an exponential moving average and can also show the raw values and a log
+x-axis. Drag across a chart to zoom in, and double-click it to zoom back out. The board
+follows the system's light or dark theme.
+
+## Training on another machine
+
+Over SSH the board starts on the training machine and does not open a browser. Instead it
+prints the command that forwards its port to your own machine:
+
+```text
+[tuffrl] board: http://127.0.0.1:6066  (logdir /data/logs)
+[tuffrl] from your own machine: ssh -N -L 6066:127.0.0.1:6066 you@gpu-box  then open http://127.0.0.1:6066
+```
+
+The board has no login. It listens on 127.0.0.1 unless `TUFFRL_BOARD_HOST` says otherwise;
+listening on another address shows your logs and config to anyone who can reach that port.
+
+## Command line and settings
+
+```bash
+tuff-rl board logs   # serve a log directory, including one TensorBoard wrote
+tuff-rl stop logs    # stop the board serving it
+```
+
+| Variable | Effect |
+| --- | --- |
+| `TUFFRL_BOARD=0` | Training scripts do not start the board. |
+| `TUFFRL_OPEN_BROWSER=0` | The board starts but no browser opens. |
+| `TUFFRL_BOARD_PORT` | Port to try first (default 6066); the next free one is used when it is taken. |
+| `TUFFRL_BOARD_HOST` | Address to listen on (default 127.0.0.1). |
+
+## How it works
+
+- **Event files.** The writer frames records the way TFRecord does (length, CRC32C, data,
+  CRC32C) and encodes the `Event` and `Summary` protobufs by hand, so neither TensorFlow nor
+  protobuf is needed. Metrics are scalar summaries, printed output uses the text plugin, and
+  the config is an HParams session, so TensorBoard's HParams tab lists the runs and groups
+  them by `group`.
+- **The board.** A standard-library HTTP server reads each event file from where it stopped,
+  and the page receives a snapshot followed by a stream of new points (server-sent events).
+  The page is a Vue app built on [TuffEx](https://www.npmjs.com/package/@talex-touch/tuffex)
+  and ships inside the wheel.
+- **One board per log directory.** `logs/.tuffrl/board.json` records which board serves the
+  directory. Scripts starting at the same moment agree on one of them to launch it, and the
+  board keeps running after training ends until `tuff-rl stop`.
+
+## Status
+
+0.1 is an alpha. The board reads images and audio but does not show them yet; that and the
+rest of the plan are in the [roadmap issues](https://github.com/talex-touch/tuff-rl/issues?q=is%3Aissue+label%3Aroadmap).
+
+## Development
+
+```bash
+cd web && pnpm install && pnpm build && cd ..   # builds the board page into src/tuffrl/board/static
+pip install -e ".[dev,system]"
+python -m pytest
+uvx ruff check .
+```
+
+See [CONTRIBUTING.md](https://github.com/talex-touch/tuff-rl/blob/main/CONTRIBUTING.md) for the rest, including how a release is made.
+
+## License
+
+[MIT](https://github.com/talex-touch/tuff-rl/blob/main/LICENSE)

tuff_rl-0.1.0/src/tuff_rl.egg-info/SOURCES.txt

@@ -0,0 +1,42 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+src/tuff_rl.egg-info/PKG-INFO
+src/tuff_rl.egg-info/SOURCES.txt
+src/tuff_rl.egg-info/dependency_links.txt
+src/tuff_rl.egg-info/entry_points.txt
+src/tuff_rl.egg-info/requires.txt
+src/tuff_rl.egg-info/top_level.txt
+src/tuffrl/__init__.py
+src/tuffrl/__main__.py
+src/tuffrl/cli.py
+src/tuffrl/compat.py
+src/tuffrl/run.py
+src/tuffrl/board/__init__.py
+src/tuffrl/board/launch.py
+src/tuffrl/board/lock.py
+src/tuffrl/board/server.py
+src/tuffrl/board/store.py
+src/tuffrl/board/static/index.html
+src/tuffrl/board/static/assets/index-D4-8ALNT.js
+src/tuffrl/board/static/assets/index-DWNZ33px.js
+src/tuffrl/board/static/assets/index-fGqPXvQK.js
+src/tuffrl/board/static/assets/index-xWSStQ1s.css
+src/tuffrl/capture/__init__.py
+src/tuffrl/capture/stdout.py
+src/tuffrl/capture/system.py
+src/tuffrl/events/__init__.py
+src/tuffrl/events/crc32c.py
+src/tuffrl/events/proto.py
+src/tuffrl/events/reader.py
+src/tuffrl/events/records.py
+src/tuffrl/events/schema.py
+src/tuffrl/events/writer.py
+tests/conftest.py
+tests/helpers.py
+tests/test_board.py
+tests/test_compat.py
+tests/test_events.py
+tests/test_run.py
+tests/test_store.py

tuff_rl-0.1.0/src/tuff_rl.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

tuff_rl-0.1.0/src/tuff_rl.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+tuff-rl = tuffrl.cli:main

tuff_rl-0.1.0/src/tuff_rl.egg-info/requires.txt

@@ -0,0 +1,8 @@
+
+[dev]
+pytest>=8.0
+tensorboard>=2.15
+tensorboardX>=2.6
+
+[system]
+psutil>=5.9

tuff_rl-0.1.0/src/tuff_rl.egg-info/top_level.txt

@@ -0,0 +1 @@
+tuffrl