AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Variational Bayesian Reinforcement Learning with Regret Bounds

Brendan O'Donoghue

NeurIPS 2021 · Bandits and online learning › RL theory and MDPs · approach: Regret bounds with function approximation

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
Replace epsilon-greedy dithering with soft-Q-learningQ-learning · DeepSeamax depth solved in 10^5 episodes: 6 -> 14Improved
Use K-learning (uncertainty-aware values) instead of soft Q-learningsoft Q-learning · DeepSea L=50time to solveImproved
Optimized temperature tau* instead of scheduled temperatureK-learning · DeepSeatime to solveImproved
Principled exploration (Thompson sampling, K-learning) instead of RLSVI, UCBVI, OQL, BEBexploration strategy · DeepSeatime to solveImproved
Remove optimism bonus and use a fixed temperatureK-learning · DeepSeatime to solveHurt

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