arXiv:2610.32125v1 Announce Type: new Abstract: Offline maximum entropy reinforcement learning seeks to estimate the optimal soft action-value function \(Q^*\) from a fixed dataset without further in...
arXiv:2608. 14401v1 Announce Type: cross Abstract: In offline RL, estimating the optimal action-value function $Q^*$ can be formulated as solving the optimal Bellman equation based solely on offline observations.
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:2510. 03494v2 Announce Type: replace Abstract: We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization.
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.
arXiv:2603. 23461v2 Announce Type: replace Abstract: We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying \emph{linear Bellman completeness} -- a fundamental setting where the Bellman backup of any linear value function remains linear.
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.
The paper introduces an operator-theoretic approach to offline reinforcement learning for continuous-time stochastic systems. By linking reinforcement learning to the Hamilton‑Jacobi‑Bellman equation, it proposes a dynamic programming recursion that represents the world model through the infinitesimal generator of controlled diffusion processes learned in a reproducing kernel Hilbert space. The authors establish global convergence of the value function under small generator‑approximation error and provide explicit finite‑sample guarantees tied to system properties such as smoothness and stability.
arXiv:2607. 17823v1 Announce Type: new Abstract: Reinforcement Learning is a cornerstone technique for modern large reasoning models.
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.
The paper introduces Q-Target Pretrained Transformers (QTPT), a method that replaces supervised behavior cloning with a Bellman-style Q‑target objective for in‑context reinforcement learning. QTPT retains the context‑conditioned Transformer architecture but learns to estimate action values using rewards and transitions from the context, rather than merely imitating offline actions. The authors provide theoretical analysis in stochastic linear bandits and finite‑horizon MDPs, demonstrating improved robustness to weak or suboptimal data, and empirically show gains over supervised pretraining on controlled RL benchmarks and extensions to D4RL Kitchen and AntMaze.
arXiv:2610.20347v1 Announce Type: new Abstract: We study the finite-sample convergence of Q-learning algorithms for the average-reward formulation of Reinforcement Learning (RL) with options. While o...