One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning
This work addresses safety-critical decision-making in offline RL, where exploration is costly or dangerous, by integrating risk-sensitivity to handle both epistemic and aleatoric uncertainties, though it is incremental as it builds on existing risk-sensitive and offline RL techniques.
The paper tackled the problem of safety-critical offline reinforcement learning by proposing a risk-sensitive model-based approach that jointly addresses distributional shift and environment stochasticity, achieving competitive performance on deterministic benchmarks and outperforming existing methods in stochastic domains.
Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic outcomes. In other words, decision-making should be risk-sensitive. Previous works on risk in offline RL combine together offline RL techniques, to avoid distributional shift, with risk-sensitive RL algorithms, to achieve risk-sensitivity. In this work, we propose risk-sensitivity as a mechanism to jointly address both of these issues. Our model-based approach is risk-averse to both epistemic and aleatoric uncertainty. Risk-aversion to epistemic uncertainty prevents distributional shift, as areas not covered by the dataset have high epistemic uncertainty. Risk-aversion to aleatoric uncertainty discourages actions that may result in poor outcomes due to environment stochasticity. Our experiments show that our algorithm achieves competitive performance on deterministic benchmarks, and outperforms existing approaches for risk-sensitive objectives in stochastic domains.