Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs
Filippo Valdettaro, A. Aldo Faisal
We address the challenge of quantifying Bayesian uncertainty and incorporating it in offline use cases of finite-state Markov Decision Processes (MDPs) with unknown dynamics. Our a…
cs.LG2023
Bag of Policies for Distributional Deep Exploration
Asen Nachkov, Luchen Li, Giulia Luise +2
Efficient exploration in complex environments remains a major challenge for reinforcement learning (RL). Compared to previous Thompson sampling-inspired mechanisms that enable temp…