AI Paper Atlas

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

Bayesian Bellman Operators

Matthew Fellows, Kristian Hartikainen, Shimon Whiteson

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 0 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
use BBO posterior (RP-BBAC) instead of posterior over Q-functions with bootstrapping (BAC) (ablation)randomised-prior Bayesian actor-critic · MountainCar-Continuous-v0 and cartpole-swingup_sparsetask successImproved
use single Q-function (SAC*) instead of double-minimum-Q trick (SAC)SAC · sparse-reward continuous controlseeds solving the taskMixed
replace SAC* with RP-BBAC (deep exploration via BBO posterior)SAC* · sparse-reward continuous controlseeds solving the taskImproved
use BBO gradient-based MSBBE minimisation instead of ignoring posterior dependence on omegaBayesian policy evaluation · 20-Link Pendulum, Puddle World, Mountain Carmean squared error stabilityImproved
add prior regularisationBBO policy evaluation · nonlinear policy evaluation taskspolicy evaluation performanceImproved
use BBO instead of local linearisation of nonlinear TDC/GTD2nonlinear policy evaluation · policy evaluation tasksmean squared errorImproved
use nonlinear Gaussian BBO instead of TD(0)Tsitsiklis counterexample · Tsitsiklis counterexampleconvergenceImproved
use BBO instead of nonlinear TDC and GTD2Tsitsiklis counterexample · Tsitsiklis counterexampleconvergence speedImproved
vary randomised prior hyperparameters (ablation)RP-BBAC · sparse-reward continuous controltask performanceNo clear effect

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