AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Scalable In-Context Q-Learning

Jinmei Liu, Fuhong Liu, Zhenhong Sun, Jianye HAO, Huaxiong Li, Bo Wang, Daoyi Dong, Chunlin Chen, Zhi Wang

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: In-context and adaptive RL · 3 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 world-model prompt construction (ablation)S-ICQL · Ant-Dir (Mixed)return: 693.87 -> 813.34Improved
add in-context Q-learning (value functions with AWR) (ablation)S-ICQL · Ant-Dir (Mixed)return: 784.07 -> 813.34Improved
add both world model and Q-learning to DPT (ablation)DPT · Cheetah-Vel (Mixed)return: -78.35 -> -35.48Improved
add world model prompt (ablation)S-ICQL · Reach (Mixed)return: 792.09 -> 806.97Improved
lower AWR temperature lambda from 1.0 to 0.01 (ablation)S-ICQL · Ant-Dir (Mixed)return: 486.23 -> 813.34Improved
lower lambda from 0.01 to 0.001 (ablation)S-ICQL · Ant-Dir (Mixed)return: 813.34 -> 767.55Hurt
increase context steps k from 4 to 6 (ablation)S-ICQL · Ant-Dir (Mixed)return: 813.34 -> 648.70Hurt
Q-learning stitching on suboptimal dataS-ICQL · training tasks, suboptimal datareturn vs best dataset returnImproved
use S-ICQL instead of DIT/IC-IQL baselinesS-ICQL · Walker-Param (Mixed)return: 391.38 -> 466.72Improved

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