CTD4 - A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics

arXiv:2405.02576v1 Announce Type: new
Abstract: Categorical Distributional Reinforcement Learning (CDRL) has demonstrated superior sample efficiency in learning complex tasks compared to conventional Reinforcement Learning (RL) approaches. However, the practical application of CDRL is encumbered by challenging projection steps, detailed parameter tuning, and domain knowledge. This paper addresses these challenges by introducing a pioneering Continuous Distributional Model-Free RL algorithm tailored for continuous action spaces. The proposed algorithm simplifies the implementation of distributional RL, adopting an actor-critic architecture wherein the critic outputs …

abstract actor actor-critic agent application arxiv categorical continuous cs.ai cs.lg domain domain knowledge efficiency fusion however knowledge multiple practical projection reinforcement reinforcement learning sample tasks type