AI Paper Atlas

Research map / Reinforcement learning / Offline RL

Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief

Kaiyang Guo, yunfeng shao, Yanhui Geng

NeurIPS 2022 · Reinforcement learning › Offline RL · approach: Pessimism and uncertainty in offline RL · 6 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
increase k from 1 to 2 (ablation)PMDB · hopper-medium (true MDP)normalized score: 106.2 -> 106.8Improved
increase k from 2 to 3 (ablation)PMDB · hopper-medium (true MDP)normalized score: 106.8 -> 90.8Hurt
increase k from 1 to 3 (ablation)PMDB · walker2d-medium (true MDP)normalized score: 82.6 -> 105.1Improved
increase k from 1 to 3 (ablation)PMDB · halfcheetah-medium (true MDP)normalized score: 70.7 -> 77.3Improved
increase k from 1 to 3 (ablation)PMDB · hopper-medium (AMG)normalized score: 91.6 -> 106.6Improved
increase k from 1 to 3 (ablation)PMDB · walker2d-medium (AMG)normalized score: 33.3 -> 82.5Improved
increase k from 1 to 3 (ablation)PMDB · halfcheetah-medium (AMG)normalized score: 63.1 -> 70.1Improved
PMDB versus MOReL (model-based baseline)PMDB · D4RL averagenormalized score: 65.1 -> 88.2Improved
PMDB versus EDAC (model-free SoTA)PMDB · D4RL averagenormalized score: 85.2 -> 88.2Improved
PMDB versus EDAC on walker2d-medium-replayPMDB · walker2d-medium-replaynormalized score: 87.1 -> 79.9Hurt
PMDB versus EDAC on halfcheetah-mediumPMDB · halfcheetah-mediumnormalized score: 65.9 -> 75.6Improved
PMDB versus CQL on hopper-medium-replayPMDB · hopper-medium-replaynormalized score: 86.3 -> 106.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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