AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

Hojoon Lee, Hanseul Cho, Hyunseung Kim, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, Chulhee Yun

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models · 1 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 Reset to DrQDrQ · Atari-100kIQM: 0.258 -> 0.343Improved
add SAM to DrQDrQ · Atari-100kIQM: 0.258 -> 0.325Improved
add LN to DrQDrQ · Atari-100kIQM: 0.258 -> 0.259No clear effect
add CReLU to DrQDrQ · Atari-100kIQM: 0.258 -> 0.256No clear effect
combine LN, SAM, CReLU and Reset (PLASTIC)DrQ · Atari-100kIQM: 0.343 -> 0.421Improved
combine all four methods (PLASTIC)DrQ · DMC-MIQM: 213 -> 565Improved
add LN to DrQDrQ · DMC-MIQM: 213 -> 412Improved
add CReLU to LN (ablation)LN · Atari-100kIQM: 0.259 -> 0.284Improved
add Reset to LN (ablation)LN · Atari-100kIQM: 0.259 -> 0.396Improved
add SAM to Reset (ablation)Reset · Atari-100kIQM: 0.343 -> 0.411Improved
add SAM and Reset to SimTPR fine-tuning at RR 4SimTPR · Atari-100kIQM: 0.243 -> 0.834Improved
add SAM on top of Reset in pretrained SimTPR at RR 2SimTPR · Atari-100kIQM: 0.709 -> 0.776Improved

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