AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Contextual Causal Dynamics for Robust Exploration in Reinforcement Learning

Jiaming Pu, Yibo Zhang, Xu Dong, Tielin Zhang, Dengpeng Xing

NeurIPS 2026 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a contextual causal dynamics model to drive intrinsic-motivation exploration in sparse-reward reinforcement learning, where causal relations may vary across contexts.

Problem

Efficient exploration in sparse-reward reinforcement learning, where existing exploration strategies assume densely coupled environment dynamics and ignore context-dependent causal mechanisms.

Approach

Models environment dynamics with context-dependent causal structure so that exploration is guided by causal relationships that may change across contexts, rather than by densely coupled dynamics models.

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