ml-agents

分支: develop-horovod

作者	SHA1	备注	提交日期
GitHub	fbf92810	Refactor Trainers to use Policy (#1098 )	6 年前
GitHub	10d2a19d	Release v0.5 (Develop) (#1203 )	6 年前
GitHub	ab5c49e8	Release v0.5 delete unityagents (#1151 ) * fixed the loggers * Modified the documentation	6 年前
GitHub	d2c320dd	Remove graph scope (#1205 ) * initial commit : Only works with PPO balance ball * Fix for recurrent * [Fix indentation error] * Fixed BC * Remove Dead code * Addressing comment : Removing dead code * Fixing the Pytest * edited comments * Removing GraphScope from the InternalBrain (#1227) * Documentation changes for removing graph scope (#1226) * Documentation changes * removed the keep checkpoint printing	6 年前
GitHub	3c9603d6	Demonstration Recorder (#1240 )	6 年前
eshvk	ef8009d9	Python code reformat via [`black`](https://github.com/ambv/black ). Features: - Reformat code via black. - Adding circleci configurations. - Add contribution guidelines. Steps to reproduce: - `pip install black` - `black <source code directory>`	6 年前
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.	5 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.	5 年前
Ervin Teng	c912d140	Make sure all tests pass on BC	5 年前
GitHub	0fe5adc2	Develop remove memories (#2795 ) * Initial commit removing memories from C# and deprecating memory fields in proto * initial changes to Python * Adding functionalities * Fixes * adding the memories to the dictionary * Fixing bugs * tweeks * Resolving bugs * Recreating the proto * Addressing comments * Passing by reference does not work. Do not merge * Fixing huge bug in Inference * Applying patches * fixing tests * Addressing comments * Renaming variable to reflect type * test	5 年前
GitHub	652488d9	check for numpy float64 (#2948 )	5 年前

11 次代码提交 (develop-horovod)