Self-Supervised RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Latest papers

10 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Self-Improving Video-to-Action Models
Oct 16, 2026Hyunwoo Ryu, Eric Ming Chen, Max Wilcoxson +1Self-Improving Agents Robot Learning from Video
Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, MA 02139, USA
TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
Oct 13, 2026Yuqian Fu, Kaiwen Jiang, Zijun Song +3Self-Supervised RL Continual Learning for LLM Agents
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · University of Science and Technology of China
ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning
Sep 28, 2026Nico Bohlinger, Jan PetersRL for Robotics Representation Learning
Technical University of Darmstadt, Germany · Robotics Institute Germany (RIG); German Research Center for AI (DFKI); hessian.AI
Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL
Aug 31, 2026Michal Korniak, Kamil Dybek, Benjamin Eysenbach +2Reinforcement Learning Offline RL
ETH Zurich · University of Warsaw · Princeton University +3
Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources
Jun 23, 2026Haoyuan Deng, Yihong Zhou, Thomas Morstyn +1Reinforcement Learning Self-Supervised RL
The University of Hong Kong, Hong Kong SAR, China · University of Oxford, Oxford, U.K. · The University of Hong Kong Shenzhen Institute of Research and Innovation, Shenzhen, China
Survival Reinforcement Learning: Toward Scalable Self-Supervised RL
May 29, 2026Franki Nguimatsia-Tiofack, Fabian Schramm, Théotime Le Hellard +1Reinforcement Learning Self-Supervised RL
Inria and École Normale Supérieure PSL Research University Paris, France
Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation
May 13, 2026Asim Osman, Sasha Abramowitz, Mark Bergh +13Reinforcement Learning Self-Supervised RL
InstaDeep, AIMS · InstaDeep, University of Stellenbosch
TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning
May 3, 2026Pritam Mishra, Coloma Ballester, Dimosthenis KaratzasReinforcement Learning Video Summarization
Universitat Pompeu Fabra, Barcelona, Spain · Universitat Autònoma de Barcelona, Barcelona, Spain
Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception
Apr 19, 2026Ashutosh Bajpai, Tamal Majumder, Akshay Nambi +1Reinforcement Learning Self-Supervised RL
Indian Institute of Technology Delhi, India · Microsoft Research, India · Indian Institute of Technology Abu Dhabi, UAE
1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities
Mar 19, 2025Kevin Wang, Ishaan Javali, Michał Bortkiewicz +2Reinforcement Learning Self-Supervised RL
Princeton University · Warsaw University of Technology · Warsaw University of Technology, Tooploox, IDEAS Research Institute

Oct 16, 2026J/K move · Enter open · S save

Self-Improving Video-to-Action Models

Hyunwoo Ryu, Eric Ming Chen, Max Wilcoxson, Vincent Sitzmann

Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, MA 02139, USA

Self-Improving Agents Robot Learning from Video Inverse Dynamics Self-Supervised RL

Open paper AskPDF arXiv

Video generative models are an emerging tool for embodied agents: they can serve as scalable visual planners, generating videos that depict how to complete previously unseen tasks. However, executing these plans typically requires a video-to-action or "inverse dynamics" model trained on large, human-collected video-action datasets, severely limiting scalability. We introduce Mirror, a self-supervised approach that learns video-to-action mappings through environment interactions, without prior action data or hand-crafted rewards. Mirror learns by attempting to follow a visual plan by executing its best guess of the underlying actions in the environment. Mirror then trains on the resulting video-action pairs, incrementally self-improving and following the visual planner more closely. Across Atari, OGBench, and DeepMind Control, Mirror outperforms leading learning-from-observation methods with learned video plans, and achieves near-expert performance with oracle plans. On Minecraft BASALT, it outperforms methods with access to expert actions or hand-engineered task knowledge. In Minecraft survival, it is the first method to acquire an iron pickaxe through self-improvement alone, without rewards or expert action labels. In the offline setting, with expert action labels but no environment interaction, it sets a new state of the art in obtaining diamonds. Our results suggest that advances in video models can translate into increasingly capable agents without a corresponding need for hand-crafted rewards or large collections of expert action data.