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:2607. 16821v1 Announce Type: cross Abstract: Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space.
By Irina Piontkovskaia, Sergey Nikolenko
The study introduces RegimeShift‑Surrogates, a streaming benchmark that tests surrogate models across eight tasks and multiple regimes. It compares revalidation—choosing the model with lowest current‑window validation loss—to stateful adaptive controllers and finds that revalidation consistently outperforms stateful methods, achieving lower mean log regret in most task‑scenario combinations. The results suggest that fresh validation evidence is more valuable than carrying over past evidence when dealing with distribution shifts.
By Harshil Lodhiya
arXiv:2609.39261v1 Announce Type: new
Abstract: Decision-focused learning (DFL) trains predictors through downstream objectives, but a different loss need not provide an independent parameter-update...
By Aojie Yuan, Haiyue Zhang, Zijian Su
arXiv:2602. 10430v2 Announce Type: replace-cross Abstract: Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures.
By Yusen Huo, Changping Wang, Yangru Huang, Jun Zhang, Jie Jiang
arXiv:2609.39634v1 Announce Type: cross
Abstract: Common policy improvement methods, including TRPO, PPO, and GRPO, estimate policy improvement under the behavioral policy's state-visitation distribu...
By Nima H. Siboni
arXiv:2607. 10362v1 Announce Type: new Abstract: Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward.
By Hanzhe You, Yonggang Zhang, Maohao Ran, Zhiqin Yang, Zhenyuan Zhang, Wei Xue, Jun Song, Xinmei Tian, Yike Guo
The paper introduces OSOL, a method for mitigating higher‑order interference in multi‑domain reinforcement learning. OSOL selects a focus domain each iteration, uses token‑level footprints from the previous checkpoint to rank rebound risk, and applies an adaptively scaled correction to the GRPO update. Experiments on Qwen3‑30B‑A3B show a 5.7% improvement over the best baseline without higher‑order differentiation.
By Zihan Lin, Xiaohan Wang, Jie Cao, Jiajun Chai, Guojun Yin, Wei Lin, Ran He
arXiv:2608.24858v1 Announce Type: new
Abstract: Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characteri...
By Lars van der Laan, Nathan Kallus
arXiv:2605. 20256v2 Announce Type: replace Abstract: Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models.
By Xikai Zhang, Yongzhi Li, Likang Xiao, Yingze Zhang, Yanhua Cheng, Quan Chen, Peng Jiang, Wenjun Wu, Liu Liu
arXiv:2609. 22041v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matching models by treating the denoising sampler as a stochastic policy that can be optimized from reward feedback.
By Yufeng Wang, Parivesh Priye, Meeshawn Marathe, Ramit Pahwa
BCPPO is a new variant of Proximal Policy Optimization that uses Bachelier-inspired cost‑prediction networks to generate a smooth penalty based on disagreement among critics. The method keeps temporal‑difference learning unchanged, applies a saturation‑aware controller to manage cost penalties, and deploys only the policy network. Across extensive experiments, BCPPO outperforms comparators in achieving higher mean returns while maintaining lower or comparable CVaR in all tested tasks.
By Dongsheng Hou, Yanqiao Chen, Yuhan Rui