AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Behavior Priors for Efficient Reinforcement Learning

Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech Marian Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess

JMLR 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration · 33 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
regularize the policy against a behavior priorKL-regularized RL on DeepMind Control walkers · Locomotion tasks (humanoid and ant)episode returnImproved
give the prior only partial (proprioceptive) information instead of full information (ablation)behavior prior · Locomotion tasksepisode returnImproved
learn with a hierarchical or structured prior rather than nonebehavior prior · Sequential Navigationlearning speedImproved

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