This is the third PR of 6 commits mentioned in #274, which features refactor of Collector to fix #245. You can check #274 for more detail. Things changed in this PR: 1. refactor collector to be more cleaner, split AsyncCollector to support asyncvenv; 2. change buffer.add api to add(batch, bffer_ids); add several types of buffer (VectorReplayBuffer, PrioritizedVectorReplayBuffer, etc.) 3. add policy.exploration_noise(act, batch) -> act 4. small change in BasePolicy.compute_*_returns 5. move reward_metric from collector to trainer 6. fix np.asanyarray issue (different version's numpy will result in different output) 7. flake8 maxlength=88 8. polish docs and fix test Co-authored-by: n+e <trinkle23897@gmail.com>
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
from tianshou.policy.base import BasePolicy
|
|
from tianshou.policy.random import RandomPolicy
|
|
from tianshou.policy.modelfree.dqn import DQNPolicy
|
|
from tianshou.policy.modelfree.c51 import C51Policy
|
|
from tianshou.policy.modelfree.qrdqn import QRDQNPolicy
|
|
from tianshou.policy.modelfree.pg import PGPolicy
|
|
from tianshou.policy.modelfree.a2c import A2CPolicy
|
|
from tianshou.policy.modelfree.ddpg import DDPGPolicy
|
|
from tianshou.policy.modelfree.ppo import PPOPolicy
|
|
from tianshou.policy.modelfree.td3 import TD3Policy
|
|
from tianshou.policy.modelfree.sac import SACPolicy
|
|
from tianshou.policy.modelfree.discrete_sac import DiscreteSACPolicy
|
|
from tianshou.policy.imitation.base import ImitationPolicy
|
|
from tianshou.policy.imitation.discrete_bcq import DiscreteBCQPolicy
|
|
from tianshou.policy.modelbase.psrl import PSRLPolicy
|
|
from tianshou.policy.multiagent.mapolicy import MultiAgentPolicyManager
|
|
|
|
|
|
__all__ = [
|
|
"BasePolicy",
|
|
"RandomPolicy",
|
|
"DQNPolicy",
|
|
"C51Policy",
|
|
"QRDQNPolicy",
|
|
"PGPolicy",
|
|
"A2CPolicy",
|
|
"DDPGPolicy",
|
|
"PPOPolicy",
|
|
"TD3Policy",
|
|
"SACPolicy",
|
|
"DiscreteSACPolicy",
|
|
"ImitationPolicy",
|
|
"DiscreteBCQPolicy",
|
|
"PSRLPolicy",
|
|
"MultiAgentPolicyManager",
|
|
]
|