ml-agents

目录树: 36528481

作者	SHA1	备注	提交日期
GitHub	4ac79742	Refactor reward signals into separate class (#2144 ) * Create new class (RewardSignal) that represents a reward signal. * Add value heads for each reward signal in the PPO model. * Make summaries agnostic to the type of reward signals, and log weighted rewards per reward signal. * Move extrinsic and curiosity rewards into this new structure. * Allow defining multiple reward signals in YAML file. Add documentation for this new structure.	6 年前
GitHub	b05c9ac1	Add environment manager for parallel environments (#2209 ) Previously in v0.8 we added parallel environments via the SubprocessUnityEnvironment, which exposed the same abstraction as UnityEnvironment while actually wrapping many parallel environments via subprocesses. Wrapping many environments with the same interface as a single environment had some downsides, however: * Ordering needed to be preserved for agents across different envs, complicating the SubprocessEnvironment logic * Asynchronous environments with steps taken out of sync with the trainer aren't viable with the Environment abstraction This PR introduces a new EnvManager abstraction which exposes a reduced subset of the UnityEnvironment abstraction and a SubprocessEnvManager implementation which replaces the SubprocessUnityEnvironment.	6 年前
GitHub	d80d5852	add some types to the reward signals (#2215 ) * WIP add some types to the reward signals * fix next_visual_in * cleanup TODO * fix bad merge	6 年前
GitHub	6a212f73	Improvements for GAIL (#2296 ) * Don't 0 value bootstrap for GAIL and Curiosity * Add gradient penalties to GAN to help with stability * Add gail_config.yaml with GAIL examples * Cleaned up trainer_config.yaml and unnecessary gammas * Documentation updates * Code cleanup	6 年前
GitHub	bd7eb286	Update reward signals in parallel with policy (#2362 )	6 年前
GitHub	689765d6	Modification of reward signals and rl_trainer for SAC (#2433 ) * 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	6 年前

6 次代码提交 (36528481-64cf-4929-9a13-116fbfc78c7d)