Index

A

action_space_dim() (in module baselax.utils.network)

actions (baselax.agents.BaseAgent.PolicyOutput attribute) (baselax.agents.DQN.PolicyOutput attribute)

B

BaseAgent (class in baselax.agents) BaseAgent.OptimOutput (class in baselax.agents) BaseAgent.OptimState (class in baselax.agents) BaseAgent.Params (class in baselax.agents) BaseAgent.PolicyOutput (class in baselax.agents)

BaseAgent.PolicyState (class in baselax.agents) baselax.utils.network module baselax.utils.seeding module

C

count (baselax.agents.BaseAgent.OptimState attribute) (baselax.agents.BaseAgent.PolicyState attribute) (baselax.agents.DQN.OptimState attribute) (baselax.agents.DQN.PolicyState attribute)

D

DQN (class in baselax.agents) DQN.OptimOutput (class in baselax.agents) DQN.OptimState (class in baselax.agents)

DQN.Params (class in baselax.agents) DQN.PolicyOutput (class in baselax.agents) DQN.PolicyState (class in baselax.agents)

E

epsilon (baselax.agents.DQN.PolicyOutput attribute)

G

global_seed() (in module baselax.utils.seeding)

I

init_optimizer() (baselax.agents.BaseAgent method) (baselax.agents.DQN method) init_params() (baselax.agents.BaseAgent method) (baselax.agents.DQN method)

init_policy() (baselax.agents.BaseAgent method) (baselax.agents.DQN method)

J

jit() (baselax.agents.BaseAgent method)

L

loss (baselax.agents.BaseAgent.OptimOutput attribute) (baselax.agents.DQN.OptimOutput attribute)

M

module baselax.utils.network baselax.utils.seeding

O

opt_state (baselax.agents.BaseAgent.OptimState attribute) (baselax.agents.DQN.OptimState attribute)

P

policy (baselax.agents.BaseAgent.Params attribute) (baselax.agents.DQN.Params attribute)

predict() (baselax.agents.BaseAgent method) (baselax.agents.DQN method)

Q

q_values (baselax.agents.DQN.PolicyOutput attribute)

T

target (baselax.agents.DQN.Params attribute)

U

update() (baselax.agents.BaseAgent method) (baselax.agents.DQN method)