AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

RePreM: Representation Pre-training with Masked Model for Reinforcement Learning

Yuanying Cai, Chuheng Zhang, Wei Shen, Xuyun Zhang, Wenjie Ruan, Longbo Huang

AAAI 2023 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 2 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
Pre-train representations with masked trajectory predictionRainbow · Atari-100k, Mixed (3M)Median HNS: 0.548 -> 0.717Improved
Pre-train representations with masked trajectory predictionRainbow · Atari-100k, Mixed (3M)Mean HNS: 0.858 -> 1.298Improved
Increase pre-training dataset quality from Random to Weak to MixedRePreM · Atari-100k, 10M samplesMedian HNS: 0.190 -> 0.774 -> 0.953Improved
Increase Mixed pre-training data from 3M to 5M to 10M samplesRePreM · Atari-100kMedian HNS: 0.717 -> 0.788 -> 0.953Improved
Increase the state encoder from Small to Medium to LargeRePreM · Atari-100k, Mixed (10M)Median HNS: 0.835 -> 0.953 -> 1.085Improved
Use RePreM representations with SACSAC · DMControl-100k, Walker-WalkScore: 42$\pm$12 -> 633$\pm$52Improved
Use RePreM representations with SACSAC · DMControl-100k, Quadruped-RunScore: 93$\pm$36 -> 579$\pm$85Improved
Fine-tune the state encoder during downstream RL (ablation)RePreM · Atari-100k, Mixed (3M)Median HNS: 0.717 -> 0.512Hurt
Use shorter sequences, T=10 instead of T=50 (ablation)RePreM · Atari-100k, Mixed (3M)Median HNS: 0.717 -> 0.322Hurt
Use the BERT masking scheme rather than replacing every masked element with a fixed token (ablation)RePreM · Atari-100k, Mixed (3M)Median HNS: 0.588 -> 0.717Improved
Use GTrXL instead of the original transformer block (ablation)RePreM · Atari-100k, Mixed (3M)Median HNS: 0.709 -> 0.717Improved
Use SimCLR loss instead of ReLIC loss (ablation)RePreM · Atari-100k, Mixed (3M)Median HNS: 0.715 -> 0.717No clear effect

Later papers that compared with this method

1 later accepted paper reports RePreM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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