[Feature] PPOTrainer #3117
Merged
[Feature] PPOTrainer #3117
Conversation
This file contains hidden or 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/3117
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
- Fixed import conflicts in torchrl/envs/async_envs.py - Fixed import conflicts in torchrl/envs/batched_envs.py - Fixed import conflicts in torchrl/envs/transforms/transforms.py - Fixed duplicate imports in torchrl/modules/llm/__init__.py - Fixed import conflicts in torchrl/trainers/trainers.py
1abf7e9 to
f9f14c2
Compare
5cc650d to
7303cf9
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
🎯 Overview
This PR introduces a comprehensive PPOTrainer feature to TorchRL, providing a high-level, configurable training interface for PPO (Proximal Policy Optimization) algorithms. The implementation includes extensive Hydra-based configuration support, comprehensive logging capabilities, and a complete training pipeline that reduces PPO implementation to ~20 lines of code.
�� Breaking Changes
frame_skipparameter to baseTrainerclassLogRewardandRecorderclasses marked for removal in v0.9 (useLogScalarandLogValidationRewardinstead)✨ Key Features
sota-implementations/ppo_trainer/with full Hydra support�� Code Quality
�� Testing
📋 Recommendations
Overall: Well-implemented feature that significantly enhances TorchRL's usability for PPO training. Breaking changes are minimal and well-justified with proper migration paths.