schola.scripts.ray.settings.PPOSettings
Class Definition
class schola.scripts.ray.settings.PPOSettings(gae_lambda=0.95, clip_param=0.2, use_gae=True)Bases: RLLibAlgorithmSpecificSettings
Dataclass for PPO (Proximal Policy Optimization) algorithm specific settings. This class defines the parameters used in the PPO algorithm, including GAE lambda, clip parameter, and whether to use GAE.
Parameters
gae_lambda
Type: float
clip_param
Type: float
use_gae
Type: bool
Attributes
clip_param
Type: float
Default: 0.2
The clip parameter for the PPO algorithm. This is the epsilon value used in the clipped surrogate objective function. It helps to limit the policy update step size to prevent large changes that could lead to performance collapse.
gae_lambda
Type: float
Default: 0.95
The lambda parameter for Generalized Advantage Estimation (GAE). This controls the trade-off between bias and variance in the advantage estimation.
name
Type: str
rllib_config
Type: Type[PPOConfig]
use_gae
Type: bool
Default: True
Whether to use Generalized Advantage Estimation (GAE) for advantage calculation. GAE is a method to reduce the variance of the advantage estimates while keeping bias low. If set to False, the standard advantage calculation will be used instead.
Methods
__init__
__init__(gae_lambda=0.95, clip_param=0.2, use_gae=True)Return type: None
get_parser
classmethod get_parser()Add the settings to the parser or subparser
get_settings_dict
get_settings_dict()Get the settings as a dictionary keyed by the correct parameter name in Ray--- title: “schola.scripts.ray.settings.PPOSettings” description: “Bases: RLLibAlgorithmSpecificSettings.” sidebar: label: “PPOSettings”
Class Definition
class schola.scripts.ray.settings.PPOSettings(gae_lambda=0.95, clip_param=0.2, use_gae=True)Bases: RLLibAlgorithmSpecificSettings
Dataclass for PPO (Proximal Policy Optimization) algorithm specific settings. This class defines the parameters used in the PPO algorithm, including GAE lambda, clip parameter, and whether to use GAE.
Parameters
gae_lambda
Type: float
clip_param
Type: float
use_gae
Type: bool
Attributes
clip_param
Type: float
Default: 0.2
The clip parameter for the PPO algorithm. This is the epsilon value used in the clipped surrogate objective function. It helps to limit the policy update step size to prevent large changes that could lead to performance collapse.
gae_lambda
Type: float
Default: 0.95
The lambda parameter for Generalized Advantage Estimation (GAE). This controls the trade-off between bias and variance in the advantage estimation.
name
Type: str
rllib_config
Type: Type[PPOConfig]
use_gae
Type: bool
Default: True
Whether to use Generalized Advantage Estimation (GAE) for advantage calculation. GAE is a method to reduce the variance of the advantage estimates while keeping bias low. If set to False, the standard advantage calculation will be used instead.
Methods
__init__
__init__(gae_lambda=0.95, clip_param=0.2, use_gae=True)Return type: None
get_parser
classmethod get_parser()Add the settings to the parser or subparser
get_settings_dict
get_settings_dict()Get the settings as a dictionary keyed by the correct parameter name in Ray