arXiv:2602. 22810v2 Announce Type: replace Abstract: In this work, we present the first theoretical analysis of multi-agent imitation learning (MAIL) in linear Markov games where both the transition dynamics and each agent's reward function are linear in some given features.
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.
arXiv:2601. 05675v2 Announce Type: replace Abstract: Hybrid action space, which combines discrete choices and continuous parameters, is prevalent in domains such as robot control and game AI.
arXiv:2606. 09758v1 Announce Type: cross Abstract: Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment.
arXiv:2512. 14617v2 Announce Type: replace-cross Abstract: Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties.
arXiv:2606. 10979v1 Announce Type: new Abstract: Many Markov decision processes (MDPs) in operations research have feasible actions that are state dependent and defined implicitly by various operational constraints.
arXiv:2602. 02762v2 Announce Type: replace Abstract: Semi-supervised imitation learning (SSIL) consists in learning a policy from a small dataset of action-labeled trajectories and a much larger dataset of action-free trajectories.
arXiv:2607. 10601v1 Announce Type: new Abstract: Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation.
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.
arXiv:2603.18965v2 Announce Type: replace Abstract: Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by pr...
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...
The paper introduces Symbolic Imitation Learning, a framework that distills an oracle policy from an offline dataset into a decision list using linear model motion primitives. By combining this with online Augmented‑Random Search tuning, the resulting interpretable policies match or surpass the oracle’s performance on 20 benchmark reinforcement learning tasks. The approach yields concise, understandable policies that domain experts can readily interpret.
This paper tackles multi‑objective imitation learning, aiming to recover policies on the Pareto front from demonstrations by multiple Pareto‑optimal experts in a Multi‑Objective Markov Decision Process. The authors propose Multi‑Output Augmented Behavioral Cloning (MA‑BC), which partitions divergent expert data and pools non‑conflicting state‑action pairs, proving that MA‑BC converges to Pareto‑optimal policies faster than independent‑dataset learners and is minimax optimal. Experiments on diverse discrete environments and a continuous Linear Quadratic Regulator confirm the algorithm’s effectiveness.