Unsupervised RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

11 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning
Oct 11, 2026Xue Wang, Yitang Li, Yiming Zhang +7Unsupervised RL Behavioral Foundation Models
University of Shanghai for Science and Technology · RoboPartyLab · Tsinghua University +2
I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning
Oct 5, 2026Ziqi Han, Yitang Li, Junhan Sun +8Representation Learning Reinforcement Learning
Tongji University · Tsinghua University · Zhejiang University +3
Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos
Oct 1, 2026Tristan Shah, Wooyoung Chung, Volodomyr Makarenko +2Reinforcement Learning Intrinsic Motivation
Texas Tech University · Purdue University
Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
Jul 1, 2026Jongchan Park, Seungjun Oh, Seungho Baek +1Reinforcement Learning Unsupervised RL
Department of Artificial Intelligence, Sungkyunkwan University, Suwon, Republic of Korea · Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea
Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
May 21, 2026Shourov Joarder, Diganta Sikdar, Ahsan Habib Akash +2KL-Regularized RL Intrinsic Reward Methods
Bangladesh University of Engineering and Technology, Bangladesh · West Virginia University, USA · University of Aberdeen, UK +2
Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
Apr 14, 2026Sohyun An, Shuibenyang Yuan, Hayeon Lee +2Unsupervised RL Cycle-Consistent Learning
Meta Superintelligence Labs · UCLA
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
Apr 7, 2026Jingbo Sun, Qichao Zhang, Songjun Tu +5Unsupervised RL Reinforcement Learning
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · Pengcheng Laboratory · School of Artificial Intelligence, University of Chinese A
When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
Mar 17, 2026Zelin Zhang, Fei Cheng, Chenhui ChuUnsupervised RL Reinforcement Learning
Kyoto University
Can We Really Learn One Representation to Optimize All Rewards?
Feb 11, 2026Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin EysenbachZero-Shot RL Representation Learning
Princeton University
Normalizing Flows are Capable Models for Continuous Control
May 29, 2025Raj Ghugare, Benjamin EysenbachNormalizing Flows Reinforcement Learning
Department of Computer Science Princeton University
ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
Dec 5, 2024Hongming Li, Zhao Yang, Xiaoxuan Liang +2Reward-Free RL Reinforcement Learning
Zhejiang Lab, Huangzhou, China · Vrije Universiteit Amsterdam, Amsterdam, the Netherlands · Computational NeuroEngineering Laboratory at the University of Florida, Gainesville, USA

Oct 11, 2026J/K move · Enter open · S save

P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning

Xue Wang, Yitang Li, Yiming Zhang, Siqin Wang+6

University of Shanghai for Science and Technology · RoboPartyLab · Tsinghua University+2

Unsupervised RL Behavioral Foundation Models Humanoid Robot Control Robot Foundation Models Terrain-Aware Robot Locomotion Reinforcement Learning

Open paper AskPDF arXiv

Behavioral foundation models (BFMs) provide humanoids with reusable repertoires of whole-body behaviors; in real-world humanoid control, the same behavioral intent may require fundamentally different motions under different terrain constraints. Covering such variation with terrain-matched demonstrations requires enumerating a combinatorial space of behaviors and terrain geometries. We introduce P-BFM, a perceptive behavioral foundation model that factorizes humanoid control into terrain-invariant intent and terrain-conditioned realization. A forward-backward representation maps motion references, target states, and reward functions into a shared intent space without terrain information, while a perceptive policy learns how to realize each intent under the surrounding terrain geometry. We further identify a complementary limitation of purely latent control: behavioral latents can preserve local motion patterns while losing precise global progress. We therefore introduce Explicit Root Instructions (ERI), which separates global transport (e.g., heading and planar velocity) from behavioral intent, while leaving local whole-body adaptation to the perceptive policy. This decomposition leads to a characteristic capability absent from conventional BFMs: one fixed intent induces different, terrain-appropriate behaviors, including changes in step height, stride, posture, foothold placement, and contacts, without terrain-specific demonstrations. Across challenging terrains, P-BFM improves motion fidelity, root-control precision, and perturbation recovery over strong baselines. A single frozen policy further supports motion tracking, goal reaching, reward inference, teleoperation, and terrain-aware recovery, and transfers zero-shot to a Unitree G1 using onboard depth sensing.