Index

A

A2C (class in chainerrl.agents) A3C (class in chainerrl.agents) ACER (class in chainerrl.agents) act() (chainerrl.agent.Agent method)

act_and_train() (chainerrl.agent.Agent method) ActionValue (class in chainerrl.action_value) Agent (class in chainerrl.agent) AL (class in chainerrl.agents)

B

Branched (class in chainerrl.links)

C

CategoricalDoubleDQN (class in chainerrl.agents) CategoricalDQN (class in chainerrl.agents)

concatenate_recurrent_states() (chainerrl.links.StatelessRecurrent method) ContinuousDeterministicDistribution (class in chainerrl.distribution) copy() (chainerrl.distribution.Distribution method)

D

DDPG (class in chainerrl.agents) DiscreteActionValue (class in chainerrl.action_value) Distribution (class in chainerrl.distribution)

DoubleDQN (class in chainerrl.agents) DoublePAL (class in chainerrl.agents) DPP (class in chainerrl.agents) DQN (class in chainerrl.agents)

E

EmpiricalNormalization (class in chainerrl.links)

entropy (chainerrl.distribution.Distribution attribute) evaluate_actions() (chainerrl.action_value.ActionValue method)

F

FactorizedNoisyLinear (class in chainerrl.links)

G

GaussianDistribution (class in chainerrl.distribution) get_recurrent_state_at() (chainerrl.links.StatelessRecurrent method)

get_state() (chainerrl.recurrent.Recurrent method) get_statistics() (chainerrl.agent.Agent method) greedy_actions (chainerrl.action_value.ActionValue attribute)

I

IQN (class in chainerrl.agents)

K

kl (chainerrl.distribution.Distribution attribute)

L

LinearInterpolationHook (class in chainerrl.experiments)

load() (chainerrl.agent.Agent method) log_prob() (chainerrl.distribution.Distribution method)

M

mask_recurrent_state_at() (chainerrl.links.StatelessRecurrent method) max (chainerrl.action_value.ActionValue attribute) MellowmaxDistribution (class in chainerrl.distribution)

MLP (class in chainerrl.links) MLPBN (class in chainerrl.links) most_probable (chainerrl.distribution.Distribution attribute)

N

n_step_forward() (chainerrl.links.StatelessRecurrent method) NatureDQNHead (class in chainerrl.links)

NIPSDQNHead (class in chainerrl.links) NSQ (class in chainerrl.agents)

P

PAL (class in chainerrl.agents) params (chainerrl.action_value.ActionValue attribute) (chainerrl.distribution.Distribution attribute)

PCL (class in chainerrl.agents) PGT (class in chainerrl.agents) PPO (class in chainerrl.agents) prob() (chainerrl.distribution.Distribution method)

Q

QuadraticActionValue (class in chainerrl.action_value)

R

Recurrent (class in chainerrl.recurrent) REINFORCE (class in chainerrl.agents)

reset_state() (chainerrl.recurrent.Recurrent method) ResidualDQN (class in chainerrl.agents)

S

sample() (chainerrl.distribution.Distribution method) SARSA (class in chainerrl.agents) save() (chainerrl.agent.Agent method) Sequence (class in chainerrl.links) set_state() (chainerrl.recurrent.Recurrent method) SingleActionValue (class in chainerrl.action_value) SoftmaxDistribution (class in chainerrl.distribution) state_kept() (in module chainerrl.recurrent)

state_reset() (in module chainerrl.recurrent) StatelessRecurrent (class in chainerrl.links) StatelessRecurrentBranched (class in chainerrl.links) StatelessRecurrentChainList (class in chainerrl.links) StatelessRecurrentSequential (class in chainerrl.links) StepHook (class in chainerrl.experiments) stop_episode() (chainerrl.agent.Agent method) stop_episode_and_train() (chainerrl.agent.Agent method)

T

TD3 (class in chainerrl.agents) to_factorized_noisy() (in module chainerrl.links)

train_agent_async() (in module chainerrl.experiments) train_agent_with_evaluation() (in module chainerrl.experiments) TRPO (class in chainerrl.agents)

U

update_state() (chainerrl.recurrent.Recurrent method)