arXiv:2607. 07855v1 Announce Type: new Abstract: Hierarchical Implicit Q-Learning (HIQL), an offline goal-conditioned RL method, selects subgoals by value-function advantages alone.
arXiv:2610.41949v1 Announce Type: cross Abstract: Few-step flow models generate samples through a handful of large denoising transitions. Applying GRPO to such models requires introducing stochastici...
The paper introduces a sample‑efficient asynchronous Q‑learning algorithm for robust reinforcement learning in infinite‑horizon, discounted robust MDPs with total‑variation uncertainty. It proves that, given a single Markovian trajectory, the algorithm achieves an entrywise ε‑approximation of the optimal Q‑function with a sample complexity bounded by a nearly minimax‑optimal expression involving the discount factor, uncertainty level, mixing time, and occupancy probability. This result improves significantly over prior bounds for robust RL.
arXiv:2602. 00781v2 Announce Type: replace Abstract: Online reinforcement learning in non-episodic, finite-horizon MDPs remains underexplored and is challenged by the need to estimate returns to a fixed terminal time.
arXiv:2610.07899v1 Announce Type: cross Abstract: Generative actors are transforming offline reinforcement learning (RL) by enabling expressive policy classes that model complex action distributions....
The monograph "Statistical Foundations of Reinforcement Learning: A Non-Asymptotic Perspective" surveys recent advances in finite-sample statistical theory for reinforcement learning. It focuses on tabular Markov decision processes and examines three sampling settings—generative model, online, and offline RL—alongside model-based and model-free algorithmic paradigms. The work emphasizes minimax-optimal sample complexity, provides self-contained analyses, and briefly explores extensions such as robust, multi-agent, federated, and human-feedback RL.
arXiv:2602. 05459v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method.
The paper introduces Generalized Proximal Policy Optimization (GPPO), a unified framework that extends PPO by incorporating $f$-divergence trust-region theory and novel estimator topologies for large language model reinforcement learning. GPPO demonstrates that different divergences produce distinct policy update dynamics and that estimator design significantly impacts performance. Experiments on eight math and coding benchmarks show GPPO surpasses standard GRPO by up to 50% in math and 14% in coding, achieving state‑of‑the‑art results.
arXiv:2609.39497v1 Announce Type: cross Abstract: Randomized smoothing certifies the probability of a fixed output event as the center of Gaussian noise moves. Feasibility or confidence filtering rep...
arXiv:2607. 19232v1 Announce Type: new Abstract: Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution.
arXiv:2606. 04845v1 Announce Type: cross Abstract: Sequential decision-making problems are often modelled as a Markov decision process (MDP).
arXiv:2610.08384v1 Announce Type: new Abstract: In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT con...
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.