Sven Mika 853d10871c [RLlib] Issue 18499: PGTrainer with training_iteration fn does not support multi-GPU. (#21376) 2 年之前
..
tests daa4304a91 [RLlib] Switch off preprocessors by default for PGTrainer. (#21008) 2 年之前
README.md 9b8218aabd [docs] Move all /latest links to /master (#11897) 4 年之前
__init__.py 3e6ba5d6d2 Revert "Revert [RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`." (#20285) 2 年之前
default_config.py 853d10871c [RLlib] Issue 18499: PGTrainer with training_iteration fn does not support multi-GPU. (#21376) 2 年之前
pg.py 49cd7ea6f9 [RLlib] Trainer sub-class PPO/DDPPO (instead of `build_trainer()`). (#20571) 2 年之前
pg_tf_policy.py 62dbf26394 [RLlib] POC: Run PGTrainer w/o the distr. exec API (Trainer's new training_iteration method). (#20984) 2 年之前
pg_torch_policy.py 3e6ba5d6d2 Revert "Revert [RLlib] POC: `PGTrainer` class that works by sub-classing, not `trainer_template.py`." (#20285) 2 年之前
utils.py 9c73871da0 [RLlib; Docs overhaul] Docstring cleanup: Evaluation (#19783) 3 年之前

README.md

Policy Gradient (PG)

An implementation of a vanilla policy gradient algorithm for TensorFlow and PyTorch.

Detailed Documentation

Implementation