Uncertainty-aware Distributional Offline Reinforcement Learning

arXiv:2403.17646v1 Announce Type: new
Abstract: Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize mitigating epistemic uncertainty by learning risk-averse policies, often overlooking environmental stochasticity. In this study, we propose an uncertainty-aware distributional offline RL method to simultaneously address both epistemic uncertainty and environmental stochasticity. We propose …

abstract arxiv challenges context cs.lg data environmental offline policies policy reinforcement reinforcement learning risk safety type uncertainty