AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Towards Empowerment Gain through Causal Structure Learning in Model-Based Reinforcement Learning

Hongye Cao, Fan Feng, Meng Fang, Shaokang Dong, Tianpei Yang, Jing Huo, Yang Gao

ICLR 2025 · 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 coupling empowerment intrinsic motivation with causal structure learning in model-based RL to improve dynamics models and agent controllability.

Problem

Model-based RL needs dynamics models that capture environment structure and let agents actively control their environment; the abstract only partially states this motivation.

Approach

Couples empowerment (mutual information between future states and actions) with causal structure learning inside the dynamics model, so that maximizing empowerment also drives learning of causal structure in MBRL.

Experimental setup

Builds on: empowerment model-based reinforcement learning

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