AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement Learning

Jianfei Ma, Wee Sun Lee

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add a reward bonus (epistemic guidance) instead of plain Mean-MDP planningEUBRL · Chain and Loopaverage returnImproved
use EUBRL instead of RMAX, even when RMAX is given a perfect prior, as the number of loops growsLoop environment · Loop (increasing loops)average returnImproved
use a more exploratory prior (EUBRL+) rather than the conservative prior (ablation)EUBRL · DeepSea (stochastic)success rateImproved
use a tied global Dirichlet prior shared across states (ablation)EUBRL · navigation-style taskssamples to converge and success rateImproved
replace variance with mutual information as the epistemic uncertainty measure (ablation)EUBRL · navigation-style taskssteps to solve and success rateMixed
use EUBRL instead of PSRL as problem size increasesDeepSea · DeepSea (deterministic)episodes to solveImproved
use EUBRL instead of BEB, which ignores posterior information in its bonusDeepSea · DeepSea (deterministic)convergence speedImproved
use EUBRL on the new LazyChain environment versus other methodsLazyChain · LazyChain (deterministic and stochastic)sample efficiency and scalabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy