mlsanityData to 14 Oct 2026

EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement Learning

arXiv 2512.15405 ↗First posted 17 Dec 2025cs.LGcited by 2

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to limited knowledge. In this paper, we propose a Bayesian reinforcement learning (RL) algorithm, textttEUBRL, which leverages epistemic guidance to achieve principled exploration. This guidance adaptively reduces per-step regret arising from estimation errors. We establish nearly minimax-optimal regret and sample complexity guarantees for a class of sufficiently expressive priors in infinite-horizon discounted MDPs. Empirically, we evaluate textttEUBRL on tasks characterized by sparse rewards, long horizons, and stochasticity. Results demonstrate that textttEUBRL achieves superior sample efficiency, scalability, and consistency.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 17 Dec 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPscited by 2
  2. 2026Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A unified uncertainty-aware exploration: Combining epistemic and aleatory uncertainty
  2. 2026Deep Epistemic Value Functions for Optimistic Exploration
  3. 2026Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds
  4. 2024Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs
  5. 2025On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
  6. 2025Uncertainty Prioritized Experience Replay
  7. 2024Safe Exploration Using Bayesian World Models and Log-Barrier Optimization
  8. 2026Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning