The paper investigates how curriculum learning affects reinforcement learning in a minimal policy learning model. It shows that when rewards are dense, curricula offer only marginal benefits, but when rewards are sparse, curricula become essential for learning to occur. The study also highlights that competing objectives—minimizing effort versus maximizing reward—create distinct optima that curricula can help navigate by reducing reward sparsity and reshaping the reward landscape.
By John J. Vastola, Ann Huang, Satpreet H. Singh, Samuel J. Gershman, Kanaka Rajan
arXiv:2607. 26370v1 Announce Type: cross Abstract: We propose a self-adaptive online learning for control method for tracking unknown target dynamics.
By Atharva Navsalkar, Hongyu Zhou, Vasileios Tzoumas
arXiv:2606. 29980v1 Announce Type: new Abstract: Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, while training only on reward-free trajectories.
By Louis Bagot (SyCoSMA), Mathieu Lefort (LIRIS, SyCoSMA, IRISA, MALT, UR), La\"etitia Matignon (SyCoSMA)
arXiv:2608. 14135v1 Announce Type: cross Abstract: Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynamics and continuously changing opponent behaviors.
By Wenhao Tang, Tianyang Chen, Zhejun Cui, Boyuan An, Jiayu Chen, Ruize Zhang, Huidong Liu, Tianyue Wu, Qingmin Liao, Fei Gao, Yu Wang, Chao Yu
arXiv:2607. 16177v1 Announce Type: new Abstract: Reinforcement learning (RL) has recently emerged as a promising feedback control strategy for nonlinear and complex dynamical systems.
By Matteo Tomasetto, Nicol\`o Botteghi, Gabriele Bruni, Andrea Manzoni
arXiv:2609.36238v1 Announce Type: new
Abstract: A goal that is close in space can be far away in time. Obstacles, terrain, and the agent's own capabilities determine how long it takes to get there. Y...
By Nico Bohlinger, Jan Peters
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)
The paper introduces MI‑SARSA, an on‑policy temporal‑difference algorithm that incorporates mutual‑information regularization to model bounded rationality in reinforcement learning. By penalizing state‑specific deviations from a learned marginal action prior, the algorithm selectively uses state information only when the expected return outweighs the informational cost, yielding a reward‑complexity tradeoff. MI‑SARSA also predicts reaction times, showing that stronger information penalties lead to simpler policies, lower control costs, and faster responses, while regularization mitigates performance loss after environmental shifts at the expense of asymptotic return.
By James Wu, Chris R. Sims
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:2607. 19232v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution.
By Kshitij Kumar Srivastava, Kshitij Jerath
arXiv:2610.20486v1 Announce Type: new
Abstract: In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions. Unlike methods that can freely sample any...
By Tongxi Wang
Limiting‑Kernel Q(λ) (LKQL) is an off‑policy value estimator that blends n‑step truncation with a long‑horizon approximation based on the limiting kernel. It maintains the computational efficiency of n‑step methods while improving policy evaluation accuracy, especially for long‑horizon tasks. The authors prove faster convergence of LKQL’s operator under aperiodicity and near‑on‑policy conditions, and demonstrate empirical gains on MuJoCo continuous‑control benchmarks.
By Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Mohamad Amin Sharifi Kolarijani