arXiv:2606. 30923v1 Announce Type: cross Abstract: Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training.
arXiv:2606. 30445v1 Announce Type: new Abstract: Online imitation learning (IL), particularly on-policy distillation, has emerged as a strong LLM post-training approach, often outperforming offline supervised fine-tuning (SFT).
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.
The paper introduces Dually Regularized AIL, a model‑free algorithm for adversarial imitation learning that jointly applies KL policy regularization and a quadratic reward penalty based on expert and learner occupancies. It proves fast convergence rates, achieving a ×O(1/K+1/N) bound on the regularized imitation gap in finite‑horizon MDPs with general function approximation, and establishes the first algorithm to attain ×O(1/ε) sample complexity in both expert demonstrations and online interactions for this regularized objective.
arXiv:2405. 16668v2 Announce Type: replace Abstract: Adversarial Imitation Learning (AIL) faces challenges with sample inefficiency because of its reliance on sufficient on-policy data to evaluate the performance of the current policy during reward function updates.
arXiv:2604. 06039v2 Announce Type: replace-cross Abstract: Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL).
arXiv:2606. 18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes.
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.
arXiv:2607. 03385v1 Announce Type: cross Abstract: Policy learning has received substantial attention with the goal of learning policies from observational data for decision-making.
arXiv:2608. 06337v1 Announce Type: cross Abstract: A monotone adversary observes an i.
arXiv:2603. 06957v2 Announce Type: replace-cross Abstract: We study post-training linear autoregressive models with outcome and process rewards.
arXiv:2512. 23075v5 Announce Type: replace-cross Abstract: Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$.
arXiv:2609.37660v1 Announce Type: new Abstract: We study nonpreemptive contextual queueing bandits in a single-server system. Each job is represented by a $d$-dimensional context vector; in each roun...