The paper introduces Survival Reinforcement Learning (SRL), an online classification-based method that extends the survival value learning framework to maximize an agent’s dwell time at target goals. SRL addresses limitations of contrastive reinforcement learning (CRL) in long-horizon, goal-conditioned tasks by avoiding the uniformity-tolerance dilemma and reducing undesirable bang-bang control behaviors. Across robotic benchmarks, SRL matches CRL on manipulation tasks and outperforms it by 2x to 8x on stable, long-horizon locomotion tasks, suggesting classification-based approaches are a promising direction for scaling reinforcement learning.
By Franki Nguimatsia-Tiofack, Fabian Schramm, Th\'eotime Le Hellard, Justin Carpentier
arXiv:2607. 08925v1 Announce Type: new Abstract: Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do.
By Elham Daneshmand, Majid Khadiv, Glen Berseth, Hsiu-Chin Lin
arXiv:2608.21830v1 Announce Type: new
Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diver...
By Chengyang Gu, Le Zhang, Jingbo Zhou, Yize Chen, Yu Shi, Siqi Bao, Zheng-Fan Wu, Hua Wu, Hui Xiong
arXiv:2608.30406v1 Announce Type: new
Abstract: Goal-conditioned reinforcement learning struggles with long horizons when rewards are sparse. While a planner can provide subgoals to guide a low-level...
By Olivier Serris, St\'ephane Doncieux, Olivier Sigaud
arXiv:2510. 17059v2 Announce Type: replace Abstract: Zero-shot imitation learning requires an agent to reproduce expert behavior from a single demonstration without additional environment interaction or gradient updates at test time.
By Kathryn Wantlin, Chongyi Zheng, Benjamin Eysenbach
arXiv:2607. 01111v1 Announce Type: cross Abstract: Robot policies inevitably encounter failures when deployed in real environments.
By Haoran Hao, Shahram Najam Syed, Jeffrey Ichnowski, Jeff Schneider
arXiv:2604.00055v2 Announce Type: replace-cross
Abstract: Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilit...
By Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya
arXiv:2509. 03206v2 Announce Type: replace-cross Abstract: Learning from reward functions and imitation learning of demonstrations are the two principal approaches for training autonomous systems that interact with an environment through action and observation.
By Zeqiang Zhang, Fabian Wurzberger, Gerrit Schmid, Sebastian Gottwald, Daniel A. Braun
arXiv:2602. 05459v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method.
By Jan Malte T\"opperwien, Aditya Mohan, Marius Lindauer
The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
By Lindsay Spoor, Aske Plaat, Thomas Moerland
The paper identifies an informational curse of horizon in goal-conditioned policy learning, showing that longer goal relabeling horizons during training can hurt policy generalization and performance. Controlled experiments with oracle planners separate training horizons from test horizons, revealing that behavioral cloning policies degrade with longer horizons while reinforcement learning mitigates this effect. The authors attribute this to reduced conditional mutual information between actions and hindsight-relabeled goals, and demonstrate that distilling short-horizon policy Jacobians into long-horizon policies improves performance, especially in combinatorial manipulation tasks.
By John L. Zhou, Yuxuan Dong, Jonathan C. Kao
The paper proves that using a permissive safety filter in reinforcement learning does not compromise asymptotic performance. By formalizing safety through a safety‑critical Markov decision process and a filtered MDP, the authors show that optimal policies in the filtered MDP achieve the same return as the best safe policy in the original setting. Experiments on Safety Gymnasium confirm zero violations during training and performance that matches or exceeds unfiltered baselines.
By Donggeon David Oh, Duy P. Nguyen, Haimin Hu, Jaime Fern\'andez Fisac