Distributional Reinforcement Learning with Online Risk-awareness Adaption

arXiv:2310.05179v2 Announce Type: replace
Abstract: The use of reinforcement learning (RL) in practical applications requires considering sub-optimal outcomes, which depend on the agent's familiarity with the uncertain environment. Dynamically adjusting the level of epistemic risk over the course of learning can tactically achieve reliable optimal policy in safety-critical environments and tackle the sub-optimality of a static risk level. In this work, we introduce a novel framework, Distributional RL with Online Risk Adaption (DRL-ORA), which can quantify the aleatory and epistemic …

abstract adjusting agent applications arxiv course cs.lg environment environments policy practical reinforcement reinforcement learning risk safety safety-critical type uncertain