* Add Soft Actor-Critic model, trainer, and policy and sac_trainer_config.yaml
* Add documentation for SAC and tweak PPO documentation to reference the new pages.
* Add tests for SAC, change simple_rl test to run both PPO and SAC.
In order for downstream packages to make use of the latest
pre-release features, we can pre-release versions of our packages.
For packages ending in `devN` pip will not install that package
version by default. This change manually updates our package version
to a development version with the idea that we can manually perform
development versions with the potential for future automated / nightly
dev releases.
* Adds evaluate_batch to reward signals. Evaluates on minibatch rather than on BrainInfo.
* Changes the way reward signal results are reported in rl_trainer so that we get the pure, unprocessed environment reward separate from the reward signals.
* Moves end_episode to rl_trainer
* Fixed bug with BCModule with RNN
- Move common functions to trainer.py, model.pyfromppo/trainer.py, ppo/policy.pyandppo/model.py'
- Introduce RLTrainer class and move most of add_experiences and some common reward
signal code there. PPO and SAC will inherit from this, not so much BC Trainer.
- Add methods to Buffer to enable sampling, truncating, and save/loading.
- Add scoping to create encoders in model.py
GitHub
Ervin T
Ervin Teng
Jeffrey Shih
Yuan Gao
Hunter
Arthur Juliani
Jonathan Harper