Index

A

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)

C

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), [1]

E

entropy (chainerrl.distribution.Distribution attribute)

evaluate_actions() (chainerrl.action_value.ActionValue method)

G

GaussianDistribution (class in chainerrl.distribution)

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

K

kl (chainerrl.distribution.Distribution attribute)

L

LinearInterpolationHook (class in chainerrl.experiments)

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

M

max (chainerrl.action_value.ActionValue attribute)

MellowmaxDistribution (class in chainerrl.distribution) most_probable (chainerrl.distribution.Distribution attribute)

N

NSQ (class in chainerrl.agents)

P

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

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

Q

QuadraticActionValue (class in chainerrl.action_value)

R

REINFORCE (class in chainerrl.agents)

ResidualDQN (class in chainerrl.agents)

S

sample() (chainerrl.distribution.Distribution method) SARSA (class in chainerrl.agents) save() (chainerrl.agent.Agent method) SingleActionValue (class in chainerrl.action_value)

SoftmaxDistribution (class in chainerrl.distribution) StepHook (class in chainerrl.experiments) stop_episode() (chainerrl.agent.Agent method) stop_episode_and_train() (chainerrl.agent.Agent method)

T

train_agent_async() (in module chainerrl.experiments)

train_agent_with_evaluation() (in module chainerrl.experiments)