memorax.algorithms.StreamAC#

class memorax.algorithms.StreamAC[source]#

Bases: object

StreamAC(cfg: memorax.algorithms.stream_ac.StreamACConfig, env: gymnax.environments.environment.Environment, env_params: gymnax.environments.environment.EnvParams, actor_network: flax.linen.module.Module, critic_network: flax.linen.module.Module)

cfg: StreamACConfig#
env: Environment#
env_params: EnvParams#
actor_network: Module#
critic_network: Module#
init(key)[source]#
Return type:

StreamACState

Parameters:

key (Array)

warmup(key, state, num_steps)[source]#
Return type:

StreamACState

Parameters:
train(key, state, num_steps)[source]#
Return type:

StreamACState

Parameters:
evaluate(key, state, num_steps)[source]#
Return type:

StreamACState

Parameters:
__init__(cfg, env, env_params, actor_network, critic_network)#
Parameters:
  • cfg (StreamACConfig)

  • env (Environment)

  • env_params (EnvParams)

  • actor_network (Module)

  • critic_network (Module)

Return type:

None