Fix Atari PPO example #780
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report
@@ Coverage Diff @@
## master #780 +/- ##
==========================================
- Coverage 91.08% 91.07% -0.01%
==========================================
Files 71 71
Lines 5082 5077 -5
==========================================
- Hits 4629 4624 -5
Misses 453 453
Flags with carried forward coverage won't be shown. Click here to find out more.
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
Trinkle23897
approved these changes
Dec 4, 2022
BFAnas
pushed a commit
to BFAnas/tianshou
that referenced
this pull request
May 5, 2024
- [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!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
make format(required)make commit-checks(required)While trying to debug Atari PPO+LSTM, I found significant gap between our Atari PPO example vs CleanRL's Atari PPO w/ EnvPool. 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 PPO experiments.
A few interesting findings:
Shoutout to CleanRL for a well-tuned Atari PPO reference implementation!