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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| regularize the policy against a behavior prior | KL-regularized RL on DeepMind Control walkers · Locomotion tasks (humanoid and ant) | episode return | Improved |
| give the prior only partial (proprioceptive) information instead of full information (ablation) | behavior prior · Locomotion tasks | episode return | Improved |
| learn with a hierarchical or structured prior rather than none | behavior prior · Sequential Navigation | learning speed | Improved |
Closest papers by meaning
- Hindsight PRIORs for Reward Learning from Human Preferences (ICLR 2024 · similarity 0.88)
- Efficient Planning with Latent Diffusion (ICLR 2024 · similarity 0.88)
- Behavioral Exploration: Learning to Explore via In-Context Adaptation (ICML 2025 · similarity 0.87)
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity (NeurIPS 2024 · similarity 0.87)
- Probabilistic Subgoal Representations for Hierarchical Reinforcement Learning (ICML 2024 · similarity 0.87)
- Prior-Guided Diffusion Planning for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
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.
