The paper introduces a Markov chain Monte Carlo (MCMC) sampling algorithm that transforms off‑policy traces into more on‑policy data for supervised finetuning (SFT). By tailoring the data distribution rather than changing the learning objective, the method allows SFT to match or surpass traditional post‑training techniques such as reinforcement learning across tasks like scientific skill acquisition, mathematical reasoning, and open‑ended expertise. The resulting models generalize better, forget less, and exhibit strong distributional performance, demonstrating that sampling can serve as a model‑native operator for broader post‑training applications.
By Aayush Karan, Sitan Chen, Yilun Du
arXiv:2609.34851v2 Announce Type: replace
Abstract: Deep reinforcement learning (DRL) algorithms for movement control are typically evaluated and benchmarked on sequential decision tasks where imprec...
By Nam Hee Kim, Markus Kirjonen, Perttu H\"am\"al\"ainen
EmbodiedMind introduces a three-stage training paradigm for embodied foundation models that tackles inefficient sample use, task imbalance, and credit assignment in long-horizon planning. The stages—Rejection Sampling-based Fine‑Tuning, Iterative Rejection GRPO, and Trie‑GRPO—filter low‑informative data, balance task difficulty, and use action prefix trees for step‑level advantage estimation. This approach yields a state‑of‑the‑art average performance of 70.02% across 18 benchmarks, notably improving long‑horizon task planning accuracy.
By Feifan Wang, Zongbing Zhang, Yu Zhang, Lingfeng Wang, Yurui Zhu, Jin Deng, Mingliang Zhang, Zhengguang Gao, Yongcheng Wang, Jin Xu, Ri Yang
arXiv:2608. 19684v1 Announce Type: new Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL.
By Tanachai Anakewat, Takayuki Osa, Tatsuya Harada
arXiv:2601. 19810v2 Announce Type: replace-cross Abstract: Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks.
By Octavio Pappalardo
arXiv:2507.06529v2 Announce Type: replace
Abstract: Bayesian optimization (BO) is a powerful paradigm for optimizing expensive black-box functions. Traditional BO methods typically rely on separate h...
By Fengxue Zhang, Yuxin Chen
arXiv:2607. 00190v1 Announce Type: cross Abstract: Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games.
By Andrzej Bia{\l}ecki, Adam Mastalerz, Han Zhou
Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based methods allow for planning by scaling test-time compute...
arXiv:2606. 06673v1 Announce Type: new Abstract: Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficient exploration.
By Ujjwal Bhatta, Utsabi Dangol, Sumaly Bajracharya, Rodrigue Rizk, KC Santosh
arXiv:2605. 29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss.
By Christoph Dann, Yishay Mansour, Mehryar Mohri
APEx is a hierarchical framework that organizes a deep research agent’s interaction history into instance-level trajectory memories and category-level procedural skills. It couples these through an Executor, Distiller, and Planner, trained with a three-stage alternating GRPO paradigm to enable reward-guided skill distillation. At test time, distilled skills act as procedural priors for online Planner adaptation via skill-guided reinforcement learning, achieving state‑of‑the‑art results on seven benchmarks, outperforming GPT‑5.4 by 14.7 points and the best memory‑augmented baseline by 3.0 points.
By Jie Ding, Rui Sun, Xinyuan Zhang, Zeyu Zhang, Xin Liu
arXiv:2610.27280v1 Announce Type: cross
Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
By Yunzhe Hu, Dong Xu