- Fix the current bug discussed in #844 in `test_ppo.py`.
- Add warning for `ActorProb ` if both `max_action ` and
`unbounded=True` are used for model initializations.
- Add warning for PGpolicy and DDPGpolicy if they find duplicate usage
of action-bounded actor and action scaling method.
Changes:
- Disclaimer in README
- Replaced all occurences of Gym with Gymnasium
- Removed code that is now dead since we no longer need to support the
old step API
- Updated type hints to only allow new step API
- Increased required version of envpool to support Gymnasium
- Increased required version of PettingZoo to support Gymnasium
- Updated `PettingZooEnv` to only use the new step API, removed hack to
also support old API
- I had to add some `# type: ignore` comments, due to new type hinting
in Gymnasium. I'm not that familiar with type hinting but I believe that
the issue is on the Gymnasium side and we are looking into it.
- Had to update `MyTestEnv` to support `options` kwarg
- Skip NNI tests because they still use OpenAI Gym
- Also allow `PettingZooEnv` in vector environment
- Updated doc page about ReplayBuffer to also talk about terminated and
truncated flags.
Still need to do:
- Update the Jupyter notebooks in docs
- Check the entire code base for more dead code (from compatibility
stuff)
- Check the reset functions of all environments/wrappers in code base to
make sure they use the `options` kwarg
- Someone might want to check test_env_finite.py
- Is it okay to allow `PettingZooEnv` in vector environments? Might need
to update docs?
- [x] I have marked all applicable categories:
+ [ ] exception-raising fix
+ [x] algorithm implementation fix
+ [ ] documentation modification
+ [ ] new feature
- [x] I have reformatted the code using `make format` (**required**)
- [x] I have checked the code using `make commit-checks` (**required**)
- [x] If applicable, I have mentioned the relevant/related issue(s)
- [x] If applicable, I have listed every items in this Pull Request
below
While trying to debug Atari PPO+LSTM, I found significant gap between
our Atari PPO example vs [CleanRL's Atari PPO w/
EnvPool](https://docs.cleanrl.dev/rl-algorithms/ppo/#ppo_atari_envpoolpy).
I tried to align our implementation with CleaRL's version, mostly in
hyper parameter choices, and got significant gain in Breakout, Qbert,
SpaceInvaders while on par in other games. After this fix, I would
suggest updating our [Atari
Benchmark](https://tianshou.readthedocs.io/en/master/tutorials/benchmark.html)
PPO experiments.
A few interesting findings:
- Layer initialization helps stabilize the training and enable the use
of larger learning rates; without it, larger learning rates will trigger
NaN gradient very quickly;
- ppo.py#L97-L101: this change helps training stability for reasons I do
not understand; also it makes the GPU usage higher.
Shoutout to [CleanRL](https://github.com/vwxyzjn/cleanrl) for a
well-tuned Atari PPO reference implementation!
* Changes to support Gym 0.26.0
* Replace map by simpler list comprehension
* Use syntax that is compatible with python 3.7
* Format code
* Fix environment seeding in test environment, fix buffer_profile test
* Remove self.seed() from __init__
* Fix random number generation
* Fix throughput tests
* Fix tests
* Removed done field from Buffer, fixed throughput test, turned off wandb, fixed formatting, fixed type hints, allow preprocessing_fn with truncated and terminated arguments, updated docstrings
* fix lint
* fix
* fix import
* fix
* fix mypy
* pytest --ignore='test/3rd_party'
* Use correct step API in _SetAttrWrapper
* Format
* Fix mypy
* Format
* Fix pydocstyle.
* When clip_loss_grad=True is passed, Huber loss is used instead of the MSE loss.
* Made the argument's name more descriptive;
* Replaced the smooth L1 loss with the Huber loss, which has an identical form to the default parametrization, but seems to be better known in this context;
* Added a fuller description to the docstring;
(Issue #512) Random start in Collector sample actions from the action space, while policies output action in a range (typically [-1, 1]) and map action to the action space. The buffer only stores unmapped actions, so the actions randomly initialized are not correct when the action range is not [-1, 1]. This may influence policy learning and particularly model learning in model-based methods.
This PR fixes it by adding an inverse operation before adding random initial actions to the buffer.
- Fixes an inconsistency in the implementation of Discrete CRR. Now it uses `Critic` class for its critic, following conventions in other actor-critic policies;
- Updates several offline policies to use `ActorCritic` class for its optimizer to eliminate randomness caused by parameter sharing between actor and critic;
- Add `writer.flush()` in TensorboardLogger to ensure real-time result;
- Enable `test_collector=None` in 3 trainers to turn off testing during training;
- Updates the Atari offline results in README.md;
- Moves Atari offline RL examples to `examples/offline`; tests to `test/offline` per review comments.
This PR implements BCQPolicy, which could be used to train an offline agent in the environment of continuous action space. An experimental result 'halfcheetah-expert-v1' is provided, which is a d4rl environment (for Offline Reinforcement Learning).
Example usage is in the examples/offline/offline_bcq.py.
- collector.collect() now returns 4 extra keys: rew/rew_std/len/len_std (previously this work is done in logger)
- save_fn() will be called at the beginning of trainer
- Batch: do not raise error when it finds list of np.array with different shape[0].
- Venv's obs: add try...except block for np.stack(obs_list)
- remove venv.__del__ since it is buggy
Change the behavior of to_numpy and to_torch: from now on, dict is automatically converted to Batch and list is automatically converted to np.ndarray (if an error occurs, raise the exception instead of converting each element in the list).
