The new proposed feature is to have trainers as generators.
The usage pattern is:
```python
trainer = OnPolicyTrainer(...)
for epoch, epoch_stat, info in trainer:
print(f"Epoch: {epoch}")
print(epoch_stat)
print(info)
do_something_with_policy()
query_something_about_policy()
make_a_plot_with(epoch_stat)
display(info)
```
- epoch int: the epoch number
- epoch_stat dict: a large collection of metrics of the current epoch, including stat
- info dict: the usual dict out of the non-generator version of the trainer
You can even iterate on several different trainers at the same time:
```python
trainer1 = OnPolicyTrainer(...)
trainer2 = OnPolicyTrainer(...)
for result1, result2, ... in zip(trainer1, trainer2, ...):
compare_results(result1, result2, ...)
```
Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
(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.
add imitation baselines for offline RL; make the choice of env/task and D4RL dataset explicit; on expert datasets, IL easily outperforms; after reading the D4RL paper, I'll rerun the exps on medium data
* Use `global_step` as the x-axis for wandb
* Use Tensorboard SummaryWritter as core with `wandb.init(..., sync_tensorboard=True)`
* Update all atari examples with wandb
Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
- change the internal API name of worker: send_action -> send, get_result -> recv (align with envpool)
- add a timing test for venvs.reset() to make sure the concurrent execution
- change venvs.reset() logic
Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
- 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
