AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Value-Distributional Model-Based Reinforcement Learning

Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters

JMLR 2024 · Reinforcement learning › Offline RL · approach: Pessimism and uncertainty in offline RL · 4 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 the proposed value-distributional critic loss (EQR target quantiles from model samples) to QR-MBPO (ablation)QR-MBPO · DMC cartpole-swingup-sparseepisode return: QR-MBPO-loss matches EQR-SAC; other QR-MBPO variants share similar lower performanceImproved
Increase buffer size and data collected under the ensemble (QR-MBPO-big) (ablation)QR-MBPO · DMC selected tasksepisode returnNo clear effect
Use model-consistent rollouts in QR-MBPO (QR-MBPO-consistent) (ablation)QR-MBPO · DMC selected tasksepisode returnNo clear effect
Increase next state-action samples for target quantiles from 1 to 25-100 (ablation)EQR-SAC · DMC cartpole-swingup-sparsesample efficiencyImproved
Sample size 1 with optimistic objective (ablation)EQR-SAC (OFU) · DMC tasksepisode returnHurt
Use number of quantiles m=1 instead of larger m (ablation)EQR-SAC · DMC tasksepisode returnHurt
Use rollout length k=1 instead of longer (ablation)EQR-SAC · DMC tasksepisode returnHurt
Use optimistic objective instead of mean objective (ablation)EQR-SAC · Mountain CarperformanceImproved
Add more optimism in policy optimization (ablation)EQR-SAC · DMC dense-reward tasksepisode returnNo clear effect
Add more optimism in policy optimization (ablation)EQR-SAC · DMC sparse-reward tasksepisode returnMixed
Use distributional QR critic instead of standard criticMBPO · DMC benchmarkepisode return: MBPO 0.1 -> QR-MBPO (mean) 476.2 on cartpole-swingup-sparseImproved
Use quantile value representation instead of critic ensembleQU-SAC · DMC benchmarkepisode return: QU-SAC 310.6 -> EQR-SAC (mean) 566.4 on cartpole-swingup-sparseImproved

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