View source on GitHub |
A CQL-SAC Agent.
Implements Conservative Q Learning from
"Conservative Q-Learning for Offline RL" Kumar et al., 2020 https://arxiv.org/abs/2006.04779
Classes
class CqlSacAgent
: A CQL-SAC Agent based on the SAC Agent.
class CqlSacLossInfo
: CqlSacLossInfo(critic_loss, actor_loss, alpha_loss, cql_loss, cql_alpha, cql_alpha_loss)