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

Jonathan Harper 481e0842 Remove the --num-runs option The "num-runs" command-line option provides the ability to run multiple identically-configured training runs in separate processes by running mlagents-learn only once. This is a rarely used ML-Agents feature, but it adds complexity to other parts of the system by adding the need to support multiprocessing and managing of ports for the parallel training runs. It also doesn't provide truly reproducible experiments, since there is no guarantee of resource isolation between the trials. This commit removes the --num-runs option, with the idea that users will manage parallel or sequential runs of the same experiment themselves in the future.		5 年前
..
components	Move add_experiences out of trainer, add Trajectories (#3067)	5 年前
ppo	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
sac	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
tests	Remove the --num-runs option	5 年前
__init__.py	Release 0.12.1 (#3078)	5 年前
action_info.py	Move add_experiences out of trainer, add Trajectories (#3067)	5 年前
agent_processor.py	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
barracuda.py	fix errors from new flake8-comprehensions (#2917)	5 年前
brain.py	[MLA-345] float visual observations (#3148)	5 年前
brain_conversion_utils.py	move (first pass)	5 年前
buffer.py	pass file mode to h5py.File() (#3165)	5 年前
curriculum.py	Allow curricula to be created without files (#3145)	5 年前
demo_loader.py	add flake8-bugbear (#3137)	5 年前
env_manager.py	Fix has_actions_for_brains check (#3087)	5 年前
exception.py	Better error handling if trainer config doesn't contain "default" section (#3063)	5 年前
learn.py	Remove the --num-runs option	5 年前
meta_curriculum.py	Allow curricula to be created without files (#3145)	5 年前
models.py	check min size for visual encoders (#3112)	5 年前
policy.py	Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment.	5 年前
rl_trainer.py	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
sampler_class.py	Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment.	5 年前
simple_env_manager.py	move (first pass)	5 年前
stats.py	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
subprocess_env_manager.py	Rename mlagents.envs to mlagents_envs (#3083)	5 年前
tensorflow_to_barracuda.py	fix errors from new flake8-comprehensions (#2917)	5 年前
tf_policy.py	Move add_experiences out of trainer, add Trajectories (#3067)	5 年前
trainer.py	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
trainer_controller.py	Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113)	5 年前
trainer_util.py	Allow curricula to be created without files (#3145)	5 年前
trajectory.py	Develop magic string + trajectory (#3122)	5 年前