Tianshou
v0.4.2
Tutorials
Deep Q Network
Basic concepts in Tianshou
Understand Batch
Multi-Agent RL
Benchmark
Cheat Sheet
API Docs
tianshou.data
tianshou.env
tianshou.policy
tianshou.trainer
tianshou.exploration
tianshou.utils
Community
Contributing to Tianshou
Contributor
Tianshou
Docs
»
Index
Edit on GitHub
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
I
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
W
_
__call__() (tianshou.exploration.BaseNoise method)
(tianshou.exploration.GaussianNoise method)
(tianshou.exploration.OUNoise method)
__getitem__() (tianshou.data.Batch method)
(tianshou.data.PrioritizedReplayBuffer method)
(tianshou.data.ReplayBuffer method)
__len__() (tianshou.data.Batch method)
(tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
(tianshou.env.BaseVectorEnv method)
__setitem__() (tianshou.data.Batch method)
A
A2CPolicy (class in tianshou.policy)
Actor (class in tianshou.utils.net.continuous)
(class in tianshou.utils.net.discrete)
actor (tianshou.policy.DiscreteSACPolicy attribute)
(tianshou.policy.SACPolicy attribute)
(tianshou.policy.TD3Policy attribute)
actor_optim (tianshou.policy.DiscreteSACPolicy attribute)
(tianshou.policy.SACPolicy attribute)
(tianshou.policy.TD3Policy attribute)
ActorProb (class in tianshou.utils.net.continuous)
add() (tianshou.data.CachedReplayBuffer method)
(tianshou.data.PrioritizedReplayBuffer method)
(tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
(tianshou.utils.MovAvg method)
AsyncCollector (class in tianshou.data)
B
BaseLogger (class in tianshou.utils)
BaseNoise (class in tianshou.exploration)
BasePolicy (class in tianshou.policy)
BaseVectorEnv (class in tianshou.env)
BasicLogger (class in tianshou.utils)
Batch (class in tianshou.data)
C
C51Policy (class in tianshou.policy)
CachedReplayBuffer (class in tianshou.data)
cat() (tianshou.data.Batch static method)
cat_() (tianshou.data.Batch method)
close() (tianshou.env.BaseVectorEnv method)
(tianshou.env.worker.EnvWorker method)
close_env() (tianshou.env.worker.DummyEnvWorker method)
(tianshou.env.worker.EnvWorker method)
(tianshou.env.worker.RayEnvWorker method)
(tianshou.env.worker.SubprocEnvWorker method)
collect() (tianshou.data.AsyncCollector method)
(tianshou.data.Collector method)
Collector (class in tianshou.data)
compute_episodic_return() (tianshou.policy.BasePolicy static method)
compute_nstep_return() (tianshou.policy.BasePolicy static method)
compute_q_value() (tianshou.policy.C51Policy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.QRDQNPolicy method)
CosineEmbeddingNetwork (class in tianshou.utils.net.discrete)
Critic (class in tianshou.utils.net.continuous)
(class in tianshou.utils.net.discrete)
critic (tianshou.policy.DiscreteSACPolicy attribute)
(tianshou.policy.SACPolicy attribute)
(tianshou.policy.TD3Policy attribute)
critic_optim (tianshou.policy.DiscreteSACPolicy attribute)
(tianshou.policy.SACPolicy attribute)
(tianshou.policy.TD3Policy attribute)
D
DDPGPolicy (class in tianshou.policy)
DiscreteBCQPolicy (class in tianshou.policy)
DiscreteCQLPolicy (class in tianshou.policy)
DiscreteCRRPolicy (class in tianshou.policy)
DiscreteSACPolicy (class in tianshou.policy)
DQNPolicy (class in tianshou.policy)
DummyEnvWorker (class in tianshou.env.worker)
DummyVectorEnv (class in tianshou.env)
E
empty() (tianshou.data.Batch static method)
empty_() (tianshou.data.Batch method)
EnvWorker (class in tianshou.env.worker)
exploration_noise() (tianshou.policy.BasePolicy method)
(tianshou.policy.DDPGPolicy method)
(tianshou.policy.DiscreteSACPolicy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.MultiAgentPolicyManager method)
F
forward() (tianshou.policy.BasePolicy method)
(tianshou.policy.DDPGPolicy method)
(tianshou.policy.DiscreteBCQPolicy method)
(tianshou.policy.DiscreteSACPolicy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.FQFPolicy method)
(tianshou.policy.ImitationPolicy method)
(tianshou.policy.IQNPolicy method)
(tianshou.policy.MultiAgentPolicyManager method)
(tianshou.policy.PGPolicy method)
(tianshou.policy.PSRLPolicy method)
(tianshou.policy.RandomPolicy method)
(tianshou.policy.SACPolicy method)
(tianshou.utils.net.common.MLP method)
(tianshou.utils.net.common.Net method)
(tianshou.utils.net.common.Recurrent method)
(tianshou.utils.net.continuous.Actor method)
(tianshou.utils.net.continuous.ActorProb method)
(tianshou.utils.net.continuous.Critic method)
(tianshou.utils.net.continuous.RecurrentActorProb method)
(tianshou.utils.net.continuous.RecurrentCritic method)
(tianshou.utils.net.discrete.Actor method)
(tianshou.utils.net.discrete.CosineEmbeddingNetwork method)
(tianshou.utils.net.discrete.Critic method)
(tianshou.utils.net.discrete.FractionProposalNetwork method)
(tianshou.utils.net.discrete.FullQuantileFunction method)
(tianshou.utils.net.discrete.ImplicitQuantileNetwork method)
FQFPolicy (class in tianshou.policy)
FractionProposalNetwork (class in tianshou.utils.net.discrete)
FullQuantileFunction (class in tianshou.utils.net.discrete)
G
gather_info() (in module tianshou.trainer)
GaussianNoise (class in tianshou.exploration)
get() (tianshou.data.ReplayBuffer method)
(tianshou.utils.MovAvg method)
get_result() (tianshou.env.worker.EnvWorker method)
(tianshou.env.worker.RayEnvWorker method)
(tianshou.env.worker.SubprocEnvWorker method)
get_weight() (tianshou.data.PrioritizedReplayBuffer method)
I
ImitationPolicy (class in tianshou.policy)
ImplicitQuantileNetwork (class in tianshou.utils.net.discrete)
init_weight() (tianshou.data.PrioritizedReplayBuffer method)
IQNPolicy (class in tianshou.policy)
is_empty() (tianshou.data.Batch method)
L
LazyLogger (class in tianshou.utils)
learn() (tianshou.policy.A2CPolicy method)
(tianshou.policy.BasePolicy method)
(tianshou.policy.C51Policy method)
(tianshou.policy.DDPGPolicy method)
(tianshou.policy.DiscreteBCQPolicy method)
(tianshou.policy.DiscreteCQLPolicy method)
(tianshou.policy.DiscreteCRRPolicy method)
(tianshou.policy.DiscreteSACPolicy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.FQFPolicy method)
(tianshou.policy.ImitationPolicy method)
(tianshou.policy.IQNPolicy method)
(tianshou.policy.MultiAgentPolicyManager method)
(tianshou.policy.NPGPolicy method)
(tianshou.policy.PGPolicy method)
(tianshou.policy.PPOPolicy method)
(tianshou.policy.PSRLPolicy method)
(tianshou.policy.QRDQNPolicy method)
(tianshou.policy.RandomPolicy method)
(tianshou.policy.SACPolicy method)
(tianshou.policy.TD3Policy method)
(tianshou.policy.TRPOPolicy method)
load_hdf5() (tianshou.data.ReplayBuffer class method)
log_test_data() (tianshou.utils.BaseLogger method)
(tianshou.utils.BasicLogger method)
log_train_data() (tianshou.utils.BaseLogger method)
(tianshou.utils.BasicLogger method)
log_update_data() (tianshou.utils.BaseLogger method)
(tianshou.utils.BasicLogger method)
M
map_action() (tianshou.policy.BasePolicy method)
mean() (tianshou.utils.MovAvg method)
miniblock() (in module tianshou.utils.net.common)
MLP (class in tianshou.utils.net.common)
module
tianshou.exploration
tianshou.trainer
tianshou.utils
tianshou.utils.net.common
tianshou.utils.net.continuous
tianshou.utils.net.discrete
MovAvg (class in tianshou.utils)
MultiAgentPolicyManager (class in tianshou.policy)
N
Net (class in tianshou.utils.net.common)
next() (tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
normalize_obs() (tianshou.env.BaseVectorEnv method)
NPGPolicy (class in tianshou.policy)
O
offline_trainer() (in module tianshou.trainer)
offpolicy_trainer() (in module tianshou.trainer)
onpolicy_trainer() (in module tianshou.trainer)
OUNoise (class in tianshou.exploration)
P
PGPolicy (class in tianshou.policy)
post_process_fn() (tianshou.policy.BasePolicy method)
PPOPolicy (class in tianshou.policy)
prev() (tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
PrioritizedReplayBuffer (class in tianshou.data)
PrioritizedReplayBufferManager (class in tianshou.data)
PrioritizedVectorReplayBuffer (class in tianshou.data)
process_fn() (tianshou.policy.A2CPolicy method)
(tianshou.policy.BasePolicy method)
(tianshou.policy.DDPGPolicy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.MultiAgentPolicyManager method)
(tianshou.policy.NPGPolicy method)
(tianshou.policy.PGPolicy method)
(tianshou.policy.PPOPolicy method)
PSRLPolicy (class in tianshou.policy)
Q
QRDQNPolicy (class in tianshou.policy)
R
RandomPolicy (class in tianshou.policy)
RayEnvWorker (class in tianshou.env.worker)
RayVectorEnv (class in tianshou.env)
Recurrent (class in tianshou.utils.net.common)
RecurrentActorProb (class in tianshou.utils.net.continuous)
RecurrentCritic (class in tianshou.utils.net.continuous)
render() (tianshou.env.BaseVectorEnv method)
(tianshou.env.worker.DummyEnvWorker method)
(tianshou.env.worker.EnvWorker method)
(tianshou.env.worker.RayEnvWorker method)
(tianshou.env.worker.SubprocEnvWorker method)
replace_policy() (tianshou.policy.MultiAgentPolicyManager method)
ReplayBuffer (class in tianshou.data)
ReplayBufferManager (class in tianshou.data)
reset() (tianshou.data.Collector method)
(tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
(tianshou.env.BaseVectorEnv method)
(tianshou.env.worker.DummyEnvWorker method)
(tianshou.env.worker.EnvWorker method)
(tianshou.env.worker.RayEnvWorker method)
(tianshou.env.worker.SubprocEnvWorker method)
(tianshou.exploration.BaseNoise method)
(tianshou.exploration.OUNoise method)
reset_buffer() (tianshou.data.Collector method)
reset_env() (tianshou.data.AsyncCollector method)
(tianshou.data.Collector method)
reset_stat() (tianshou.data.Collector method)
restore_data() (tianshou.utils.BaseLogger method)
(tianshou.utils.BasicLogger method)
RunningMeanStd (class in tianshou.utils)
S
SACPolicy (class in tianshou.policy)
sample() (tianshou.data.ReplayBuffer method)
sample_index() (tianshou.data.PrioritizedReplayBuffer method)
(tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
save_data() (tianshou.utils.BaseLogger method)
(tianshou.utils.BasicLogger method)
save_hdf5() (tianshou.data.ReplayBuffer method)
seed() (tianshou.env.BaseVectorEnv method)
(tianshou.env.worker.DummyEnvWorker method)
(tianshou.env.worker.EnvWorker method)
(tianshou.env.worker.RayEnvWorker method)
(tianshou.env.worker.SubprocEnvWorker method)
send_action() (tianshou.env.worker.DummyEnvWorker method)
(tianshou.env.worker.EnvWorker method)
(tianshou.env.worker.RayEnvWorker method)
(tianshou.env.worker.SubprocEnvWorker method)
set_agent_id() (tianshou.policy.BasePolicy method)
set_batch() (tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
set_eps() (tianshou.policy.DQNPolicy method)
set_exp_noise() (tianshou.policy.DDPGPolicy method)
shape() (tianshou.data.Batch property)
ShmemVectorEnv (class in tianshou.env)
split() (tianshou.data.Batch method)
stack() (tianshou.data.Batch static method)
stack_() (tianshou.data.Batch method)
std() (tianshou.utils.MovAvg method)
step() (tianshou.env.BaseVectorEnv method)
(tianshou.env.worker.EnvWorker method)
SubprocEnvWorker (class in tianshou.env.worker)
SubprocVectorEnv (class in tianshou.env)
sync_weight() (tianshou.policy.DDPGPolicy method)
(tianshou.policy.DiscreteCRRPolicy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.SACPolicy method)
(tianshou.policy.TD3Policy method)
T
TD3Policy (class in tianshou.policy)
test_episode() (in module tianshou.trainer)
tianshou.exploration
module
tianshou.trainer
module
tianshou.utils
module
tianshou.utils.net.common
module
tianshou.utils.net.continuous
module
tianshou.utils.net.discrete
module
to_numpy() (tianshou.data.Batch method)
to_torch() (tianshou.data.Batch method)
train() (tianshou.policy.DDPGPolicy method)
(tianshou.policy.DiscreteBCQPolicy method)
(tianshou.policy.DQNPolicy method)
(tianshou.policy.SACPolicy method)
(tianshou.policy.TD3Policy method)
training (tianshou.policy.A2CPolicy attribute)
(tianshou.policy.BasePolicy attribute)
(tianshou.policy.C51Policy attribute)
(tianshou.policy.DDPGPolicy attribute)
(tianshou.policy.DiscreteBCQPolicy attribute)
(tianshou.policy.DiscreteCQLPolicy attribute)
(tianshou.policy.DiscreteCRRPolicy attribute)
(tianshou.policy.DiscreteSACPolicy attribute)
(tianshou.policy.DQNPolicy attribute)
(tianshou.policy.FQFPolicy attribute)
(tianshou.policy.ImitationPolicy attribute)
(tianshou.policy.IQNPolicy attribute)
(tianshou.policy.MultiAgentPolicyManager attribute)
(tianshou.policy.NPGPolicy attribute)
(tianshou.policy.PGPolicy attribute)
(tianshou.policy.PPOPolicy attribute)
(tianshou.policy.PSRLPolicy attribute)
(tianshou.policy.QRDQNPolicy attribute)
(tianshou.policy.RandomPolicy attribute)
(tianshou.policy.SACPolicy attribute)
(tianshou.policy.TD3Policy attribute)
(tianshou.policy.TRPOPolicy attribute)
(tianshou.utils.net.common.MLP attribute)
(tianshou.utils.net.common.Net attribute)
(tianshou.utils.net.common.Recurrent attribute)
(tianshou.utils.net.continuous.Actor attribute)
(tianshou.utils.net.continuous.ActorProb attribute)
(tianshou.utils.net.continuous.Critic attribute)
(tianshou.utils.net.continuous.RecurrentActorProb attribute)
(tianshou.utils.net.continuous.RecurrentCritic attribute)
(tianshou.utils.net.discrete.Actor attribute)
(tianshou.utils.net.discrete.CosineEmbeddingNetwork attribute)
(tianshou.utils.net.discrete.Critic attribute)
(tianshou.utils.net.discrete.FractionProposalNetwork attribute)
(tianshou.utils.net.discrete.FullQuantileFunction attribute)
(tianshou.utils.net.discrete.ImplicitQuantileNetwork attribute)
TRPOPolicy (class in tianshou.policy)
U
unfinished_index() (tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
update() (tianshou.data.Batch method)
(tianshou.data.PrioritizedReplayBuffer method)
(tianshou.data.ReplayBuffer method)
(tianshou.data.ReplayBufferManager method)
(tianshou.policy.BasePolicy method)
(tianshou.utils.RunningMeanStd method)
update_weight() (tianshou.data.PrioritizedReplayBuffer method)
V
value_mask() (tianshou.policy.BasePolicy static method)
VectorReplayBuffer (class in tianshou.data)
W
wait() (tianshou.env.worker.DummyEnvWorker static method)
(tianshou.env.worker.EnvWorker static method)
(tianshou.env.worker.RayEnvWorker static method)
(tianshou.env.worker.SubprocEnvWorker static method)
write() (tianshou.utils.BaseLogger method)
(tianshou.utils.BasicLogger method)
(tianshou.utils.LazyLogger method)