* Remove flag `eval_mode` from Collector.collect
* Replace flag `is_eval` in BasePolicy with `is_within_training_step` (negating usages)
and set it appropriately in BaseTrainer
# Changes
## Dependencies
- New extra "eval"
## Api Extension
- `Experiment` and `ExperimentConfig` now have a `name`, that can
however be overridden when `Experiment.run()` is called
- When building an `Experiment` from an `ExperimentConfig`, the user has
the option to add info about seeds to the name.
- New method in `ExperimentConfig` called
`build_default_seeded_experiments`
- `SamplingConfig` has an explicit training seed, `test_seed` is
inferred.
- New `evaluation` package for repeating the same experiment with
multiple seeds and aggregating the results (important extension!).
Currently in alpha state.
- Loggers can now restore the logged data into python by using the new
`restore_logged_data`
## Breaking Changes
- `AtariEnvFactory` (in examples) now receives explicit train and test
seeds
- `EnvFactoryRegistered` now requires an explicit `test_seed`
- `BaseLogger.prepare_dict_for_logging` is now abstract
---------
Co-authored-by: Maximilian Huettenrauch <m.huettenrauch@appliedai.de>
Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
Co-authored-by: Michael Panchenko <35432522+MischaPanch@users.noreply.github.com>
Closes: https://github.com/aai-institute/tianshou/issues/1116
### API Extensions
- Batch received new method: `to_torch_`. #1117
### Breaking Changes
- The method `to_torch` in `data.utils.batch.Batch` is not in-place
anymore. Instead, a new method `to_torch_` does the conversion in-place.
#1117
Closes: https://github.com/thu-ml/tianshou/issues/1086
### Api Extensions
- Batch received new method: `to_numpy_`. #1098
- `to_dict` in Batch supports also non-recursive conversion. #1098
- Batch `__eq__` now implemented, semantic equality check of batches is
now possible. #1098
### Breaking Changes
- The method `to_numpy` in `data.utils.batch.Batch` is not in-place
anymore. Instead, a new method `to_numpy_` does the conversion in-place.
#1098
Closes#952
- `SamplingConfig` supports `batch_size=None`. #1077
- tests and examples are covered by `mypy`. #1077
- `NetBase` is more used, stricter typing by making it generic. #1077
- `utils.net.common.Recurrent` now receives and returns a
`RecurrentStateBatch` instead of a dict. #1077
---------
Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
Closes: #1058
### Api Extensions
- Batch received two new methods: `to_dict` and `to_list_of_dicts`.
#1063
- `Collector`s can now be closed, and their reset is more granular.
#1063
- Trainers can control whether collectors should be reset prior to
training. #1063
- Convenience constructor for `CollectStats` called
`with_autogenerated_stats`. #1063
### Internal Improvements
- `Collector`s rely less on state, the few stateful things are stored
explicitly instead of through a `.data` attribute. #1063
- Introduced a first iteration of a naming convention for vars in
`Collector`s. #1063
- Generally improved readability of Collector code and associated tests
(still quite some way to go). #1063
- Improved typing for `exploration_noise` and within Collector. #1063
### Breaking Changes
- Removed `.data` attribute from `Collector` and its child classes.
#1063
- Collectors no longer reset the environment on initialization. Instead,
the user might have to call `reset`
expicitly or pass `reset_before_collect=True` . #1063
- VectorEnvs now return an array of info-dicts on reset instead of a
list. #1063
- Fixed `iter(Batch(...)` which now behaves the same way as
`Batch(...).__iter__()`. Can be considered a bugfix. #1063
---------
Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
- Added nbqa to pyproject.toml
- Resolved mypy issues on notebooks and related files
- Conducting ruff checks on notebooks
- Add DataclassPPrintMixin for better stats representation
- Improved Notebooks wording and explanations
Resolve: #1004
Related to #974
This PR adds strict typing to the output of `update` and `learn` in all
policies. This will likely be the last large refactoring PR before the
next release (0.6.0, not 1.0.0), so it requires some attention. Several
difficulties were encountered on the path to that goal:
1. The policy hierarchy is actually "broken" in the sense that the keys
of dicts that were output by `learn` did not follow the same enhancement
(inheritance) pattern as the policies. This is a real problem and should
be addressed in the near future. Generally, several aspects of the
policy design and hierarchy might deserve a dedicated discussion.
2. Each policy needs to be generic in the stats return type, because one
might want to extend it at some point and then also extend the stats.
Even within the source code base this pattern is necessary in many
places.
3. The interaction between learn and update is a bit quirky, we
currently handle it by having update modify special field inside
TrainingStats, whereas all other fields are handled by learn.
4. The IQM module is a policy wrapper and required a
TrainingStatsWrapper. The latter relies on a bunch of black magic.
They were addressed by:
1. Live with the broken hierarchy, which is now made visible by bounds
in generics. We use type: ignore where appropriate.
2. Make all policies generic with bounds following the policy
inheritance hierarchy (which is incorrect, see above). We experimented a
bit with nested TrainingStats classes, but that seemed to add more
complexity and be harder to understand. Unfortunately, mypy thinks that
the code below is wrong, wherefore we have to add `type: ignore` to the
return of each `learn`
```python
T = TypeVar("T", bound=int)
def f() -> T:
return 3
```
3. See above
4. Write representative tests for the `TrainingStatsWrapper`. Still, the
black magic might cause nasty surprises down the line (I am not proud of
it)...
Closes#933
---------
Co-authored-by: Maximilian Huettenrauch <m.huettenrauch@appliedai.de>
Co-authored-by: Michael Panchenko <m.panchenko@appliedai.de>
This PR adds a new method for getting actions from an env's observation
and info. This is useful for standard inference and stands in contrast
to batch-based methods that are currently used in training and
evaluation. Without this, users have to do some kind of gymnastics to
actually perform inference with a trained policy. I have also added a
test for the new method.
In future PRs, this method should be included in the examples (in the
the "watch" section).
To add this required improving multiple typing things and, importantly,
_simplifying the signature of `forward` in many policies!_ This is a
**breaking change**, but it will likely affect no users. The `input`
parameter of forward was a rather hacky mechanism, I believe it is good
that it's gone now. It will also help with #948 .
The main functional change is the addition of `compute_action` to
`BasePolicy`.
Other minor changes:
- improvements in typing
- updated PR and Issue templates
- Improved handling of `max_action_num`
Closes#981
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>
- [X] I have marked all applicable categories:
+ [ ] exception-raising fix
+ [ ] algorithm implementation fix
+ [ ] documentation modification
+ [X] 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
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>
- [ ] I have marked all applicable categories:
+ [x] exception-raising fix
+ [ ] algorithm implementation fix
+ [ ] documentation modification
+ [ ] new feature
- [ ] I have reformatted the code using `make format` (**required**)
- [ ] I have checked the code using `make commit-checks` (**required**)
- [ ] If applicable, I have mentioned the relevant/related issue(s)
- [ ] If applicable, I have listed every items in this Pull Request
below
I'm developing a new PettingZoo environment. It is a two players turns
board game.
```
obs_space = dict(
board = gym.spaces.MultiBinary([8, 8]),
player = gym.spaces.Tuple([gym.spaces.Discrete(8)] * 2),
other_player = gym.spaces.Tuple([gym.spaces.Discrete(8)] * 2)
)
self._observation_space = gym.spaces.Dict(spaces=obs_space)
self._action_space = gym.spaces.Tuple([gym.spaces.Discrete(8)] * 2)
...
# this cache ensures that same space object is returned for the same
agent
# allows action space seeding to work as expected
@functools.lru_cache(maxsize=None)
def observation_space(self, agent):
# gymnasium spaces are defined and documented here:
https://gymnasium.farama.org/api/spaces/
return self._observation_space
@functools.lru_cache(maxsize=None)
def action_space(self, agent):
return self._action_space
```
My test is:
```
def test_with_tianshou():
action = None
# env = gym.make('qwertyenv/CollectCoins-v0', pieces=['rock', 'rock'])
env = CollectCoinsEnv(pieces=['rock', 'rock'], with_mask=True)
def another_action_taken(action_taken):
nonlocal action
action = action_taken
# Wrapping the original environment as to make sure a valid action will
be taken.
env = EnsureValidAction(
env,
env.check_action_valid,
env.provide_alternative_valid_action,
another_action_taken
)
env = PettingZooEnv(env)
policies = MultiAgentPolicyManager([RandomPolicy(), RandomPolicy()],
env)
env = DummyVectorEnv([lambda: env])
collector = Collector(policies, env)
result = collector.collect(n_step=200, render=0.1)
```
I have also a wrapper that may be redundant as of Tianshou capability to action_mask, yet it is still part of the code:
```
from typing import TypeVar, Callable
import gymnasium as gym
from pettingzoo.utils.wrappers import BaseWrapper
Action = TypeVar("Action")
class ActionWrapper(BaseWrapper):
def __init__(self, env: gym.Env):
super().__init__(env)
def step(self, action):
action = self.action(action)
self.env.step(action)
def action(self, action):
pass
def render(self, *args, **kwargs):
self.env.render(*args, **kwargs)
class EnsureValidAction(ActionWrapper):
"""
A gym environment wrapper to help with the case that the agent wants to
take invalid actions.
For example consider a Chess game, where you let the action_space be any
piece moving to any square on the board,
but then when a wrong move is taken, instead of returing a big negative
reward, you just take another action,
this time a valid one. To make sure the learning algorithm is aware of
the action taken, a callback should be provided.
"""
def __init__(self, env: gym.Env,
check_action_valid: Callable[[Action], bool],
provide_alternative_valid_action: Callable[[Action], Action],
alternative_action_cb: Callable[[Action], None]):
super().__init__(env)
self.check_action_valid = check_action_valid
self.provide_alternative_valid_action = provide_alternative_valid_action
self.alternative_action_cb = alternative_action_cb
def action(self, action: Action) -> Action:
if self.check_action_valid(action):
return action
alternative_action = self.provide_alternative_valid_action(action)
self.alternative_action_cb(alternative_action)
return alternative_action
```
To make above work I had to patch a bit PettingZoo (opened a pull-request there), and a small patch here (this PR).
Maybe I'm doing something wrong, yet I fail to see it.
With my both fixes of PZ and of Tianshou, I have two tests, one of the environment by itself, and the other as of above.
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?
This allows, for instance, to change the action registered into the
buffer when the environment modify the action.
Useful in offline learning for instance, since the true actions are in a
dataset and the actions of the agent are ignored.
- [ ] I have marked all applicable categories:
+ [ ] exception-raising fix
+ [ ] algorithm implementation fix
+ [ ] documentation modification
+ [X] new feature
- [X ] I have reformatted the code using `make format` (**required**)
- [X] I have checked the code using `make commit-checks` (**required**)
- [] If applicable, I have mentioned the relevant/related issue(s)
- [X] If applicable, I have listed every items in this Pull Request
below
## implementation
I implemented HER solely as a replay buffer. It is done by temporarily
directly re-writing transitions storage (`self._meta`) during the
`sample_indices()` call. The original transitions are cached and will be
restored at the beginning of the next sampling or when other methods is
called. This will make sure that. for example, n-step return calculation
can be done without altering the policy.
There is also a problem with the original indices sampling. The sampled
indices are not guaranteed to be from different episodes. So I decided
to perform re-writing based on the episode. This guarantees that the
sampled transitions from the same episode will have the same re-written
goal. This also make the re-writing ratio calculation slightly differ
from the paper, but it won't be too different if there are many episodes
in the buffer.
In the current commit, HER replay buffer only support 'future' strategy
and online sampling. This is the best of HER in term of performance and
memory efficiency.
I also add a few more convenient replay buffers
(`HERVectorReplayBuffer`, `HERReplayBufferManager`), test env
(`MyGoalEnv`), gym wrapper (`TruncatedAsTerminated`), unit tests, and a
simple example (examples/offline/fetch_her_ddpg.py).
## verification
I have added unit tests for almost everything I have implemented.
HER replay buffer was also tested using DDPG on [`FetchReach-v3`
env](https://github.com/Farama-Foundation/Gymnasium-Robotics). I used
default DDPG parameters from mujoco example and didn't tune anything
further to get this good result! (train script:
examples/offline/fetch_her_ddpg.py).
* 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.
