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