benchmarl.algorithms.MaddpgConfig

class MaddpgConfig(share_param_critic: bool, loss_function: str, delay_value: bool, use_tanh_mapping: bool)[source]

Bases: AlgorithmConfig

Configuration dataclass for Maddpg.

share_param_critic: bool = <dataclasses._MISSING_TYPE object>
loss_function: str = <dataclasses._MISSING_TYPE object>
delay_value: bool = <dataclasses._MISSING_TYPE object>
use_tanh_mapping: bool = <dataclasses._MISSING_TYPE object>
static associated_class() Type[Algorithm][source]

The algorithm class associated to the config

static supports_continuous_actions() bool[source]

If the algorithm supports continuous actions

static supports_discrete_actions() bool[source]

If the algorithm supports discrete actions

static on_policy() bool[source]

If the algorithm has to be run on policy or off policy

static has_centralized_critic() bool[source]

If the algorithm uses a centralized critic