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
arXiv:2607. 08971v1 Announce Type: new Abstract: The stochastic linear bandit, where actions are represented as vectors and rewards are linear, is a central paradigm for sequential decision making.
By Gautam Dasarathy, Vineet Gattani, Lalit Jain
In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family of approximations rel...
arXiv:2607. 08340v1 Announce Type: cross Abstract: Q-learning is a fundamental algorithm in reinforcement learning (RL) for solving discounted Markov decision processes (MDPs) when the transition kernel is unknown.
By Donghwan Lee
arXiv:2602. 11399v2 Announce Type: replace-cross Abstract: As unsupervised pretraining becomes increasingly ubiquitous in reinforcement learning, a more thorough theoretical understanding of these methods becomes of equal importance to their empirical success.
By Chongyi Zheng, Royina Karegoudra Jayanth, Benjamin Eysenbach
arXiv:2603. 08558v3 Announce Type: replace Abstract: Learning compact state representations in Markov Decision Processes (MDPs) has proven crucial for addressing the curse of dimensionality in large-scale reinforcement learning (RL) problems.
By Tommaso Giorgi, Pierriccardo Olivieri, Keyue Jiang, Laura Toni, Matteo Papini
arXiv:2608. 02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon.
By Abdelghani Ghanem, Mounir Ghogho
The paper introduces state abstractions that preserve the difference of Q‑functions for offline reinforcement learning, aiming to exclude irrelevant dynamics from rich state data. It proposes a dynamic generalization of the R‑learner that uses orthogonal estimation and sparse learning to estimate the Q‑function contrast, achieving faster convergence and consistency under a margin condition. Experiments on simulated and simulator‑augmented real data show variance reductions and demonstrate that the necessary information for sequential decision‑making can be smaller than that required for full state prediction.
By Defu Cao, Angela Zhou
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)
The paper introduces a model‑free continuous‑time reinforcement learning algorithm that learns from a fixed batch of discrete‑time off‑policy data. It builds on the PhiBE‑Q framework to create a PhiBE‑PI policy iteration that uses a single state‑action critic, avoiding explicit drift or diffusion estimation. The authors provide a local end‑to‑end suboptimality guarantee under linear function approximation, analyze error propagation from discretization, function approximation, and finite samples, and reveal a bias‑variance trade‑off where finer time discretization can worsen statistical error.
By Chaorui Yao, Yuming Paul Zhang, Lin Yang, Yuhua Zhu
arXiv:2608. 07301v1 Announce Type: new Abstract: We study what can be recovered about the transition probabilities of a Markov decision process from optimal actions alone.
By Neal Batra
The paper introduces robust successor features, a method that extends the successor representation to handle uncertainty in both reward functions and transition kernels within linear Markov Decision Processes. It provides a theoretical bound on Generalized Policy Improvement that quantifies performance loss due to mismatched dynamics, and demonstrates the approach on grid-based benchmarks against prior methods that consider only reward or transition differences.
By Erik Nikulski, Yamen Habib, Vicen\c{c} Gomez, Anders Jonsson, Rub\'en Moreno-Bote, Javier Segovia-Aguas