CGAR: Critic Guided Action Redistribution in Reinforcement Leaning. (arXiv:2206.11494v1 [cs.LG])

Web: http://arxiv.org/abs/2206.11494

Training a game-playing reinforcement learning agent requires multiple
interactions with the environment. Ignorant random exploration may cause a
waste of time and resources. It's essential to alleviate such waste. As
discussed in this paper, under the settings of the off-policy actor critic
algorithms, we demonstrate that the critic can bring more expected discounted
rewards than or at least equal to the actor. Thus, the Q value predicted by the
critic is a better signal to redistribute the action originally sampled …

arxiv lg reinforcement