arXiv Machine Learning October 3, 2026 By Tristan Shah, Wooyoung Chung, Volodomyr Makarenko, Juan Wachs, Stas Tiomkin

Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos

Read the original on arXiv Machine Learning →

The paper introduces Forward CIP (F‑CIP), an RL‑native formulation of the Controllable Information Production objective that relies solely on system dynamics, eliminating the need for domain‑specific information variable selection. F‑CIP is proven compatible with reinforcement learning and, when applied to existing algorithms, enables agents to autonomously discover primitive behaviors such as balancing and maintaining controllability. Coupled with a simple forward‑velocity reward, the method yields coordinated gaits like hopping and running without reward engineering.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 8

Self-evolving LLM agents with in-distribution Optimization

arXiv:2606. 07367v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge.

By Yudi Zhang, Meng Fang, Zhenfang Chen, Mykola Pechenizkiy

llms agents reinforcement-learning

arXiv AI

Jul 3

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

arXiv:2605. 11020v2 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories.

By Anish Diwan, Davide Tateo, Christopher E. Mower, Haitham Bou-Ammar, Jan Peters, Oleg Arenz

reinforcement-learning benchmarks safety

arXiv AI

Aug 28

Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics

The paper introduces Residual Reward Models (RRM) to enhance preference‑based reinforcement learning (PbRL) in robotics. RRMs decompose the true reward into a prior component—such as a heuristic, language‑generated, or IRL‑derived reward—and a learned residual that is trained with human preferences. Experiments on Meta‑World, DM‑Control, and a physical Franka Panda robot show that RRMs markedly improve sample efficiency and accelerate policy learning compared to standard PbRL methods.

By Chenyang Cao, Miguel Rogel-Garc\'ia, Mohamed Nabail, Xueqian Wang, Nicholas Rhinehart

reinforcement-learning robotics fine-tuning

arXiv Machine Learning

Jun 11

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

arXiv:2606. 12372v1 Announce Type: cross Abstract: Human-in-the-loop reinforcement learning (HiL-RL) has emerged as an effective paradigm for real-world robotic manipulation, enabling online policy improvement with human guidance.

By Haoyuan Deng, Yitong Gao, Yudong Lin, Haichao Liu, Zhenyu Wu, Ziwei Wang

agents reinforcement-learning robotics benchmarks

arXiv Machine Learning

Jun 29

Regularized Reward-Punishment Reinforcement Learning

arXiv:2606. 28152v1 Announce Type: new Abstract: We propose KL-Coupled Policy Regularization (KCPR), a policy coordination framework for Reward-Punishment Reinforcement Learning (RPRL).

By Jiexin Wang, Eiji Uchibe

reinforcement-learning robotics safety data-engineering

arXiv AI

Sep 16

Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation

arXiv:2609.17325v1 Announce Type: new Abstract: Biological cells can be viewed as individual, interacting agents whose collective dynamics give rise to adaptive behaviour at multiple levels of organi...

By Anatoly Belikov

agents reinforcement-learning

One email a morning, machine-written

Related stories

Self-evolving LLM agents with in-distribution Optimization

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning

Regularized Reward-Punishment Reinforcement Learning

Intrinsic Motivation in Reinforcement Learning: A Research Agenda for Adaptive Self-Organisation