ml-agents

Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目，它使游戏和模拟能够作为训练智能代理的环境。

unity3d unity unity-tech reinforcement-le deep-learning deep-reinforcement-learning neural-networks

文件历史

GitHub babe9e2f Develop remove academy done (#2519 ) * Initial Commit * Remove the Academy Done flag from the protobuf definitions * remove global_done in the environment * Removed irrelevant unitTests * Remove the max_step from the Academy inspector * Removed global_done from the python scripts * Modified and removed some tests * This actually does not break either curriculum nor generalization training * Replace global_done with reserved. Addressing Chris Elion's comment regarding the deprecation of the global_done field. We will use a reserved field to make sure the global done does not get replaced in the future causing errors. * Removed unused fake brain * Tested that the first call to step was the same as a reset call * black formating * Added documentation changes * Editing the migrating doc * Addressing comments on the Migrating doc * Addressing comments : - Removing dead code - Resolving forgotten merged conflicts - Editing documentations...		5 年前
..
test_demo_dir	GAIL and Pretraining (#2118)	6 年前
BasicLearning.pb	Modified the Basic Environment (#1347)	6 年前
__init__.py	Fixed imports, all tests are passing.	6 年前
mock_brain.py	Add more extensive tests for BC trainer (#2506)	5 年前
test.demo	Demonstration Recorder (#1240)	6 年前
test_barracuda_converter.py	Python code reformat via [`black`](https://github.com/ambv/black).	6 年前
test_bc.py	Add more extensive tests for BC trainer (#2506)	5 年前
test_bcmodule.py	Fix issue where SAC encoder type is always simple (#2548)	5 年前
test_buffer.py	Refactor Trainer and Model (#2360)	5 年前
test_curriculum.py	Python code reformat via [`black`](https://github.com/ambv/black).	6 年前
test_demo_loader.py	GAIL and Pretraining (#2118)	6 年前
test_learn.py	Move trainer initialization into a utility function (#2412)	5 年前
test_meta_curriculum.py	Python code reformat via [`black`](https://github.com/ambv/black).	6 年前
test_multigpu.py	Update reward signals in parallel with policy (#2362)	5 年前
test_policy.py	Add environment manager for parallel environments (#2209)	6 年前
test_ppo.py	Fix bug in add_rewards_output and add test (#2442)	5 年前
test_reward_signals.py	Fix issue where SAC encoder type is always simple (#2548)	5 年前
test_rl_trainer.py	Add 2 visual obs test	5 年前
test_sac.py	Fix issue where SAC encoder type is always simple (#2548)	5 年前
test_simple_rl.py	Develop remove academy done (#2519)	5 年前
test_trainer_controller.py	Develop remove academy done (#2519)	5 年前
test_trainer_metrics.py	Python code reformat via [`black`](https://github.com/ambv/black).	6 年前
test_trainer_util.py	Move trainer initialization into a utility function (#2412)	5 年前
testdcvis.demo	GAIL and Pretraining (#2118)	6 年前