Closes#947
This removes all kwargs from all policy constructors. While doing that,
I also improved several names and added a whole lot of TODOs.
## Functional changes:
1. Added possibility to pass None as `critic2` and `critic2_optim`. In
fact, the default behavior then should cover the absolute majority of
cases
2. Added a function called `clone_optimizer` as a temporary measure to
support passing `critic2_optim=None`
## Breaking changes:
1. `action_space` is no longer optional. In fact, it already was
non-optional, as there was a ValueError in BasePolicy.init. So now
several examples were fixed to reflect that
2. `reward_normalization` removed from DDPG and children. It was never
allowed to pass it as `True` there, an error would have been raised in
`compute_n_step_reward`. Now I removed it from the interface
3. renamed `critic1` and similar to `critic`, in order to have uniform
interfaces. Note that the `critic` in DDPG was optional for the sole
reason that child classes used `critic1`. I removed this optionality
(DDPG can't do anything with `critic=None`)
4. Several renamings of fields (mostly private to public, so backwards
compatible)
## Additional changes:
1. Removed type and default declaration from docstring. This kind of
duplication is really not necessary
2. Policy constructors are now only called using named arguments, not a
fragile mixture of positional and named as before
5. Minor beautifications in typing and code
6. Generally shortened docstrings and made them uniform across all
policies (hopefully)
## Comment:
With these changes, several problems in tianshou's inheritance hierarchy
become more apparent. I tried highlighting them for future work.
---------
Co-authored-by: Dominik Jain <d.jain@appliedai.de>
Closes#914
Additional changes:
- Deprecate python below 11
- Remove 3rd party and throughput tests. This simplifies install and
test pipeline
- Remove gym compatibility and shimmy
- Format with 3.11 conventions. In particular, add `zip(...,
strict=True/False)` where possible
Since the additional tests and gym were complicating the CI pipeline
(flaky and dist-dependent), it didn't make sense to work on fixing the
current tests in this PR to then just delete them in the next one. So
this PR changes the build and removes these tests at the same time.
Preparation for #914 and #920
Changes formatting to ruff and black. Remove python 3.8
## Additional Changes
- Removed flake8 dependencies
- Adjusted pre-commit. Now CI and Make use pre-commit, reducing the
duplication of linting calls
- Removed check-docstyle option (ruff is doing that)
- Merged format and lint. In CI the format-lint step fails if any
changes are done, so it fulfills the lint functionality.
---------
Co-authored-by: Jiayi Weng <jiayi@openai.com>
# Goals of the PR
The PR introduces **no changes to functionality**, apart from improved
input validation here and there. The main goals are to reduce some
complexity of the code, to improve types and IDE completions, and to
extend documentation and block comments where appropriate. Because of
the change to the trainer interfaces, many files are affected (more
details below), but still the overall changes are "small" in a certain
sense.
## Major Change 1 - BatchProtocol
**TL;DR:** One can now annotate which fields the batch is expected to
have on input params and which fields a returned batch has. Should be
useful for reading the code. getting meaningful IDE support, and
catching bugs with mypy. This annotation strategy will continue to work
if Batch is replaced by TensorDict or by something else.
**In more detail:** Batch itself has no fields and using it for
annotations is of limited informational power. Batches with fields are
not separate classes but instead instances of Batch directly, so there
is no type that could be used for annotation. Fortunately, python
`Protocol` is here for the rescue. With these changes we can now do
things like
```python
class ActionBatchProtocol(BatchProtocol):
logits: Sequence[Union[tuple, torch.Tensor]]
dist: torch.distributions.Distribution
act: torch.Tensor
state: Optional[torch.Tensor]
class RolloutBatchProtocol(BatchProtocol):
obs: torch.Tensor
obs_next: torch.Tensor
info: Dict[str, Any]
rew: torch.Tensor
terminated: torch.Tensor
truncated: torch.Tensor
class PGPolicy(BasePolicy):
...
def forward(
self,
batch: RolloutBatchProtocol,
state: Optional[Union[dict, Batch, np.ndarray]] = None,
**kwargs: Any,
) -> ActionBatchProtocol:
```
The IDE and mypy are now very helpful in finding errors and in
auto-completion, whereas before the tools couldn't assist in that at
all.
## Major Change 2 - remove duplication in trainer package
**TL;DR:** There was a lot of duplication between `BaseTrainer` and its
subclasses. Even worse, it was almost-duplication. There was also
interface fragmentation through things like `onpolicy_trainer`. Now this
duplication is gone and all downstream code was adjusted.
**In more detail:** Since this change affects a lot of code, I would
like to explain why I thought it to be necessary.
1. The subclasses of `BaseTrainer` just duplicated docstrings and
constructors. What's worse, they changed the order of args there, even
turning some kwargs of BaseTrainer into args. They also had the arg
`learning_type` which was passed as kwarg to the base class and was
unused there. This made things difficult to maintain, and in fact some
errors were already present in the duplicated docstrings.
2. The "functions" a la `onpolicy_trainer`, which just called the
`OnpolicyTrainer.run`, not only introduced interface fragmentation but
also completely obfuscated the docstring and interfaces. They themselves
had no dosctring and the interface was just `*args, **kwargs`, which
makes it impossible to understand what they do and which things can be
passed without reading their implementation, then reading the docstring
of the associated class, etc. Needless to say, mypy and IDEs provide no
support with such functions. Nevertheless, they were used everywhere in
the code-base. I didn't find the sacrifices in clarity and complexity
justified just for the sake of not having to write `.run()` after
instantiating a trainer.
3. The trainers are all very similar to each other. As for my
application I needed a new trainer, I wanted to understand their
structure. The similarity, however, was hard to discover since they were
all in separate modules and there was so much duplication. I kept
staring at the constructors for a while until I figured out that
essentially no changes to the superclass were introduced. Now they are
all in the same module and the similarities/differences between them are
much easier to grasp (in my opinion)
4. Because of (1), I had to manually change and check a lot of code,
which was very tedious and boring. This kind of work won't be necessary
in the future, since now IDEs can be used for changing signatures,
renaming args and kwargs, changing class names and so on.
I have some more reasons, but maybe the above ones are convincing
enough.
## Minor changes: improved input validation and types
I added input validation for things like `state` and `action_scaling`
(which only makes sense for continuous envs). After adding this, some
tests failed to pass this validation. There I added
`action_scaling=isinstance(env.action_space, Box)`, after which tests
were green. I don't know why the tests were green before, since action
scaling doesn't make sense for discrete actions. I guess some aspect was
not tested and didn't crash.
I also added Literal in some places, in particular for
`action_bound_method`. Now it is no longer allowed to pass an empty
string, instead one should pass `None`. Also here there is input
validation with clear error messages.
@Trinkle23897 The functional tests are green. I didn't want to fix the
formatting, since it will change in the next PR that will solve #914
anyway. I also found a whole bunch of code in `docs/_static`, which I
just deleted (shouldn't it be copied from the sources during docs build
instead of committed?). I also haven't adjusted the documentation yet,
which atm still mentions the trainers of the type
`onpolicy_trainer(...)` instead of `OnpolicyTrainer(...).run()`
## Breaking Changes
The adjustments to the trainer package introduce breaking changes as
duplicated interfaces are deleted. However, it should be very easy for
users to adjust to them
---------
Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
- 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.
- [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!
* 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;
- 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).
This PR focus on some definition change of trainer to make it more friendly to use and be consistent with typical usage in research papers, typically change `collect-per-step` to `step-per-collect`, add `update-per-step` / `episode-per-collect` accordingly, and modify the documentation.
