IMPALASettings

Full path: schola.scripts.rllib.settings.IMPALASettings

Dataclass for IMPALA (Importance Weighted Actor-Learner Architecture) algorithm specific settings. This class defines the parameters used in the IMPALA algorithm, including V-trace settings for off-policy correction.

IMPALASettings(vtrace = True, vtrace_clip_rho_threshold = 1.0,
               vtrace_clip_pg_rho_threshold = 1.0)

Bases: RllibAlgorithmSpecificSettings

Parameters

• vtrace (bool)

• vtrace_clip_rho_threshold (Annotated)

• vtrace_clip_pg_rho_threshold (Annotated)

Methods

init

__init__(vtrace = True, vtrace_clip_rho_threshold = 1.0,
         vtrace_clip_pg_rho_threshold = 1.0)

Parameters

• vtrace (bool)

• vtrace_clip_rho_threshold (Annotated)

• vtrace_clip_pg_rho_threshold (Annotated)

---

get_settings_dict

get_settings_dict()

Get the settings as a dictionary keyed by the correct parameter name in Ray

Attributes

vtrace

vtrace

Whether to use the V-trace algorithm for off-policy correction in the IMPALA algorithm. V-trace is a method to correct the bias introduced by using off-policy data for training. It helps to ensure that the value estimates are more accurate and stable.

---

vtrace_clip_pg_rho_threshold

vtrace_clip_pg_rho_threshold

The clip threshold for V-trace rho values in the policy gradient.

---

vtrace_clip_rho_threshold

vtrace_clip_rho_threshold

The clip threshold for V-trace rho values.

---

name

name

---

rllib_config

rllib_config