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:2608. 09853v1 Announce Type: cross Abstract: General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from large-scale heterogeneous corpora remains underexplored.
By Dongchi Huang, Hongyin Zhang, Bohan Hou, Siteng Huang, Zhian Su, Hang Guo, Tong Lu, Zhaofeng Xu, Jiahao Tang, Jianfei Yang, Donglin Wang, Peixi Peng, Mingxiu Chen, Deli Zhao, Xin Li
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
arXiv:2609.37519v1 Announce Type: cross
Abstract: Video-based policy learning is particularly promising, as it illustrates target behaviors without requiring action annotations or embodiment-matched...
By Merve Atasever, Keyan Azbijari, Cagan Bakirci, Bo-Ruei Huang, Tolga Izdas, Zahra Shahrooei, Richard Yang, Erdem Biyik, Jyotirmoy V. Deshmukh
arXiv:2607. 00442v1 Announce Type: cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpretability of learned policies and lack explicit control over gait behaviors.
By Merve Atasever, Cagan Bakirci, Alfredo Reina Corona, Keyan Azbijari, Jyotirmoy V. Deshmukh
Dynin‑Robotics introduces an omnimodal masked‑diffusion backbone, Dynin‑Omni, that jointly represents language, visual observations, goals, and actions as discrete tokens. By conditioning on different spans, the same model learns action prediction, next‑observation prediction, goal‑state prediction, and trajectory‑to‑instruction reconstruction, enabling test‑time scaling through goal prediction and action‑candidate evaluation. The system, pretrained on 1.33 million trajectories from 48 Open X‑Embodiment datasets, achieves competitive performance on LIBERO, zero‑shot LIBERO‑Plus, and a 78.4 % success rate on a Franka Research 3 robot, while a block‑parallel implementation speeds up action decoding by up to 29.2×.
By Hoeun Lee, Jaeik Kim, Jusang Oh, Jinhyeok Kim, Geon Choi, Hyeonggeun Kim, Jaeyoung Do
arXiv:2304.10041v2 Announce Type: replace
Abstract: This work investigates formal policy synthesis for continuous-state stochastic dynamic systems subject to high-level specifications expressed in li...
By Lening Li, Zhentian Qian, Jianan Xia, Qiren Geng, Huasheng Zhang, Liang Hu, Qishuang Li, Junqiang Lou
arXiv:2604. 12474v3 Announce Type: replace-cross Abstract: In many robotic tasks, agents must traverse a sequence of spatial regions to complete a mission.
By Lidor Erez, Shahaf S. Shperberg, Ayal Taitler
arXiv:2608.30378v1 Announce Type: cross
Abstract: Direct vision-language-action policies generate continuous robot actions efficiently, but standard behavior cloning leaves two complementary gaps: th...
By Botong Zhao, Fang Yu, Tim, Senhua Zhu, Xinyuan Chen, Yue Lu
arXiv:2604. 13733v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit assignment.
By Angelo Moroncelli, Roberto Zanetti, Marco Maccarini, Loris Roveda
arXiv:2609.38383v1 Announce Type: cross
Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...
By Deqian Kong, Guangyan Sun, Sheng Cheng, Sirui Xie, Bo Pang, Jianwen Xie, Tony Geng, Caiwen Ding, Ying Nian Wu
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
By Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn