ml-agents

作者	SHA1	备注	提交日期
GitHub	c258b1c3	Move 'take_action' into Policy class (#1669 ) * Move 'take_action' into Policy class This refactor is part of Actor-Trainer separation. Since policies will be distributed across actors in separate processes which share a single trainer, taking an action should be the responsibility of the policy. This change makes a few smaller changes: * Combines `take_action` logic between trainers, making it more generic * Adds an `ActionInfo` data class to be more explicit about the data returned by the policy, only used by TrainerController and policy for now. * Moves trainer stats logic out of `take_action` and into `add_experiences` * Renames 'take_action' to 'get_action'	6 年前
GitHub	2671e1a0	Enable mypy in precommit checks (#2177 ) * WIP precommit on top level * update CI * circleci fixes * intentionally fail black * use --show-diff-on-failure in CI * fix command order * rebreak a file * apply black * WIP enable mypy * run mypy on each package * fix trainer_metrics mypy errors * more mypy errors * more mypy * Fix some partially typed functions * types for take_action_outputs * fix formatting * cleanup * generate stubs for proto objects * fix ml-agents-env mypy errors * disallow-incomplete-defs for gym-unity * Add CI notes to CONTRIBUTING.md	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	ccb7eab4	Remove {text,custom} {action,observations} (#2839 ) * delete text actions and obs * delete custom actions and obs * regenerate protos * cleanup C# * format * fix tests * fix base env signature * doc cleanup	5 年前
GitHub	90db165f	Add --namespace-packages to mypy for mlagents (#3075 )	5 年前
GitHub	2fd305e7	Move add_experiences out of trainer, add Trajectories (#3067 )	5 年前
Ervin Teng	e577d5ea	Fix some mypy issues and remove unused code	5 年前
GitHub	4c241a80	Only send previous action and current BrainInfo (#3187 ) This PR makes it so that the env_manager only sends one current BrainInfo and the previous actions (if any) to the AgentManager. The list of agents was added to the ActionInfo and used appropriately.	5 年前
GitHub	f058b18c	Replace BrainInfos with BatchedStepResult (#3207 )	5 年前
GitHub	ca96b293	Move advance() logic for environment manager out of trainer_controller (#3234 ) This PR moves the AgentManagers from the TrainerController into the env_manager. This way, the TrainerController only needs to create the components (Trainers, AgentManagers) and call advance() on the EnvManager and the Trainers.	5 年前
GitHub	88d3ec3e	Merge master into hybrid actions staging branch (#4704 )	4 年前
Andrew Cohen	f73b9dba	update policy to not use critic	4 年前
GitHub	338af2ec	Move the Critic into the Optimizer (#4939 ) Co-authored-by: Ervin Teng <ervin@unity3d.com>	4 年前

13 次代码提交 (develop-horovod)