AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

Siming Lan, Rui Zhang, Qi Yi, Jiaming Guo, Shaohui Peng, Yunkai Gao, Fan Wu, Ruizhi Chen, Zidong Du, Xing Hu, Xishan Zhang, Ling Li and 1 more

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 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 contrastive loss among modules (ablation)CMTA · MT10-Mixedmax smoothed success rate: 79.46 -> 82.07Improved
add contrastive loss among modules (ablation)CMTA · MT50-Mixedmax smoothed success rate: 62.66 -> 71.69Improved
add contrastive loss to CARE (ablation)CARE · MT10-Mixedmax smoothed success rate: 61.35 -> 65.24Improved
add contrastive loss to CARE (ablation)CARE · MT50-Mixedmax smoothed success rate: 45.00 -> 47.61Improved
add contrastive loss (ablation)CMTA · MT10-Fixed and MT50-Fixedsuccess rateNo clear effect
remove temporal information (LSTM state) from attention (ablation)CMTA · MT10-Fixed and MT10-Mixedsuccess rateImproved
increase experts from 2 to 6 (ablation)CMTA · MT10-Mixed (1.0M steps)max smoothed success rate: 52.53 -> 78.49Improved
increase experts from 6 to 20 (ablation)CMTA · MT10-Mixed (1.0M steps)max smoothed success rate: 78.49 -> 75.01Hurt
CMTA vs CARECMTA · MT50-Mixedmax smoothed success rate: 45.00 -> 71.69Improved
CMTA vs CARECMTA · MT10-Fixedmax smoothed success rate: 68.03 -> 78.95Improved
CMTA vs single-task SAC upper boundCMTA · MT10-Mixedmax smoothed success rate: 71.11 -> 82.07Improved
CMTA vs single-task SAC upper boundCMTA · MT10-Fixedmax smoothed success rate: 64.33 -> 78.95Improved

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