ASTEROID is a student–teacher supervised learning framework that learns efficient test‑time exploration in partially observable sequential decision problems. By training a history‑conditioned student on on‑policy contexts while a privileged expert provides action labels conditioned on that history, the student learns to search while uncertain and exploit once the hidden state is revealed. Across eleven diverse environments, ASTEROID achieves roughly twice the returns under fixed exploration budgets, uses about 100× fewer interactions than reinforcement learning baselines, and transfers well to vision‑denied real‑world robot manipulation, improving success by +40% over standard distillation.
By Sriyash Poddar, Yanda Bao, Jacob Krantz, Matthew Chang, Xavier Puig, Roozbeh Mottaghi, Natasha Jaques, Abhishek Gupta
arXiv:2608. 07228v1 Announce Type: new Abstract: When a reinforcement learning agent cannot observe the full state, we usually blame its policies: it cannot see enough to represent a good one.
By Idil G\"ozel (University College London)
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
By Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters
arXiv:2606. 05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many responses and reward each with a single bit indicating whether the final answer is correct.
By Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad
arXiv:2603. 15956v3 Announce Type: replace-cross Abstract: Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data.
By Zifan Xu, Ran Gong, Maria Vittoria Minniti, Kausik Sivakumar, Ahmet Salih Gundogdu, Eric Rosen, Riedana Yan, Tushar Kusnur, Zixing Wang, Di Deng, Peter Stone, Xiaohan Zhang, Karl Schmeckpeper
arXiv:2607. 29617v1 Announce Type: cross Abstract: Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model training.
By Luca Viano, Antoine Moulin, Audrey Huang, Volkan Cevher, Philip Amortila, Dylan J. Foster
The paper introduces a statistical framework for Inverse Entropy-regularized Reinforcement Learning that resolves the non-uniqueness of reward functions by combining entropy regularization with a least-squares reconstruction of the reward from the soft Bellman residual. It models expert demonstrations as a Markov chain, estimates the expert policy via penalized maximum likelihood, and provides high-probability bounds on the excess Kullback–Leibler divergence between the estimated and true policies. These results yield non-asymptotic minimax optimal convergence rates for the least-squares reward function, highlighting the trade-offs among smoothing, model complexity, and sample size.
By Denis Belomestny, Alexey Naumov, Artemy Rubtsov, Sergey Samsonov
arXiv:2605.06387v4 Announce Type: replace-cross
Abstract: On-policy distillation (OPD) trains a student on its own trajectories with token-level teacher feedback and often outperforms off-policy dist...
By Nan Jia, Haojin Yang, Xing Ma, Jiesong Lian, Shuailiang Zhang, Weipeng Zhang, Ke Zeng, Xunliang Cai, Zequn Sun
The paper introduces BUMEX, a reinforcement learning exploration strategy that leverages a set of prior models containing the true transition kernel and reward function. By optimizing over this model set, the method derives upper and lower bounds on the Q‑function to guide exploration, providing theoretical guarantees of convergence to the optimal policy. When the model set follows a bounded‑parameter MDP structure, the optimization becomes convex, enabling finite‑time convergence under mild assumptions and demonstrating accelerated learning in simulations.
By J. S. van Hulst, W. P. M. H. Heemels, D. J. Antunes
The paper introduces On‑Policy Warmup (OPW), a teacher‑guided training stage where a student agent learns from a teacher on its own interaction trajectories before switching to reinforcement learning with verifiable rewards (RLVR). OPW differs from traditional imitation by focusing on states generated by the student’s own decisions, including imperfect actions and recovery situations. The authors provide a theoretical link between on‑policy reverse‑KL distillation and trajectory‑level distribution matching, showing that, under a competent teacher and low distillation loss, OPW can lower bound initial verifier success and reduce reward‑discovery complexity, thereby accelerating RLVR performance.
By Yitong Qiao, Tiantian He, Lei Liu, Yue Shen, Jian Wang, Jinjie Gu, Zhixuan Chu
EVOL is a framework that uses a knowledge‑tracing simulator to generate per‑learner expert demonstrations via evolutionary search, and then trains a deployment‑free policy that distills these demonstrations into a feed‑forward learner. The method employs an asymmetric actor‑critic architecture, where the actor plans blindly as in real deployment while the critic has access to privileged simulator state during training. Across three educational datasets and varying path lengths, EVOL outperforms eight baselines and shows that the quality of evolutionary experts, rather than the imitation objective, drives final performance.
By Geonwoo Bang, Dongho Kim, Moohong Min
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