The paper introduces Cross-Behavior Policy Optimization (CBPO), a method that unifies offline demonstrations and policy-generated rollouts into a single regression loss using a fixed-reference target. CBPO eliminates the need for separate supervised fine‑tuning and reinforcement learning objectives, allowing positive and negative offline completions, reference responses, and current and historical rollouts to share a common reward‑labeled format and replay buffer. Experiments on two model scales and four mathematical reasoning benchmarks show that CBPO, especially the CBPO‑Unified variant, outperforms baseline methods in avg@32 and pass@32 metrics, with historical rollouts providing additional gains.
By Du Cheng, Junyu Lu, Jingfan Zhang, Yuzhuo Zhang, Haoxuan Jia, Shichao Weng
The paper introduces Safe Contrastive Reinforcement Learning (Safe-CRL), a method that corrects bias in contrastive RL caused by failure-terminated Markov decision processes. By applying mass-weighted InfoNCE and a log-survival-mass score, Safe-CRL uses only a one-bit failure signal to improve survival and goal-reaching performance across twelve robot navigation and locomotion tasks. The approach demonstrates complex failure-avoidance behaviors and completes the theoretical foundation of contrastive RL under failure termination.
By Guopeng Li, Yiyang Duan, Yiru Jiao, Chengcheng Xu
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
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
The paper introduces Q-Target Pretrained Transformers (QTPT), a method that replaces supervised behavior cloning with a Bellman-style Q‑target objective for in‑context reinforcement learning. QTPT retains the context‑conditioned Transformer architecture but learns to estimate action values using rewards and transitions from the context, rather than merely imitating offline actions. The authors provide theoretical analysis in stochastic linear bandits and finite‑horizon MDPs, demonstrating improved robustness to weak or suboptimal data, and empirically show gains over supervised pretraining on controlled RL benchmarks and extensions to D4RL Kitchen and AntMaze.
By Yichen Lin, Xuyuan Xiong, Xue Wang, Xiangfu Meng, Mike Mingcheng Wei, Tao Yao
arXiv:2609.33875v2 Announce Type: replace-cross
Abstract: Outcome-only reinforcement learning gives software engineering (SWE) agents a terminal success signal but little direct guidance about interm...
By Yuanhao Li, Hongbo Wang, Xuhong Chen, Yiming Cao, Xunzhu Tang
arXiv:2608.20909v1 Announce Type: new
Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
By Xuyao Lin, Yixiang Shan, Jinru Duan, Tao Yang, Xinyu Zhao, Runyu Lei, Yiming Zhao, Jiaxin Fan, Zongbao Feng, Peng Jia
arXiv:2608.30640v1 Announce Type: new
Abstract: While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open q...
By Michal Korniak, Kamil Dybek, Benjamin Eysenbach, Marco Bagatella, Micha{\l} Bortkiewicz
arXiv:2606. 18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes.
By Xuanfei Ren, Tengyang Xie
arXiv:2606. 09115v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers a path to policy improvement from logged data alone, using historical returns or other measurable outcomes as world feedback.
By Lena Krieger, Xuan Zhao, Zhuo Cao, Qin Wang, Hanno Scharr, Ira Assent
arXiv:2609.07461v1 Announce Type: new
Abstract: We consider reinforcement learning in environments with dynamics that undergo an irreversible phase transition governed by a hidden temporal pattern. T...
By Jan Corazza, Daniil Kaminskyi, Simon Lutz, Patrick Nossol, Hadi Partovi Aria, Zhe Xu, Daniel Neider
arXiv:2607. 17003v1 Announce Type: cross Abstract: Imitation learning enables learning a policy in an unknown environment with a latent reward signal using expert demonstrations, but it struggles when the imitator's and expert's observations are mismatched and unobserved confounders are present in expert demonstrations.
By Eylam Tagor, Mingxuan Li, Elias Bareinboim