Bypassing the simulator: Near-optimal adversarial linear contextual bandits
We consider the adversarial linear contextual bandit problem, where the loss vectors are
selected fully adversarially and the per-round action set (ie the context) is drawn from a fixed …
selected fully adversarially and the per-round action set (ie the context) is drawn from a fixed …
Settling the sample complexity of online reinforcement learning
A central issue lying at the heart of online reinforcement learning (RL) is data efficiency.
While a number of recent works achieved asymptotically minimal regret in online RL, the …
While a number of recent works achieved asymptotically minimal regret in online RL, the …
Sharp variance-dependent bounds in reinforcement learning: Best of both worlds in stochastic and deterministic environments
We study variance-dependent regret bounds for Markov decision processes (MDPs).
Algorithms with variance-dependent regret guarantees can automatically exploit …
Algorithms with variance-dependent regret guarantees can automatically exploit …
Tackling heavy-tailed rewards in reinforcement learning with function approximation: Minimax optimal and instance-dependent regret bounds
While numerous works have focused on devising efficient algorithms for reinforcement
learning (RL) with uniformly bounded rewards, it remains an open question whether sample …
learning (RL) with uniformly bounded rewards, it remains an open question whether sample …
Noise-adaptive thompson sampling for linear contextual bandits
Linear contextual bandits represent a fundamental class of models with numerous real-
world applications, and it is critical to develop algorithms that can effectively manage noise …
world applications, and it is critical to develop algorithms that can effectively manage noise …
Is behavior cloning all you need? understanding horizon in imitation learning
Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision
making task by learning from demonstrations, and has been widely applied to robotics …
making task by learning from demonstrations, and has been widely applied to robotics …
Variance-aware regret bounds for stochastic contextual dueling bandits
Dueling bandits is a prominent framework for decision-making involving preferential
feedback, a valuable feature that fits various applications involving human interaction, such …
feedback, a valuable feature that fits various applications involving human interaction, such …
Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
We study infinite-horizon average-reward Markov decision processes (AMDPs) in the
context of general function approximation. Specifically, we propose a novel algorithmic …
context of general function approximation. Specifically, we propose a novel algorithmic …
More benefits of being distributional: Second-order bounds for reinforcement learning
In this paper, we prove that Distributional Reinforcement Learning (DistRL), which learns the
return distribution, can obtain second-order bounds in both online and offline RL in general …
return distribution, can obtain second-order bounds in both online and offline RL in general …
Reinforcement learning from human feedback with active queries
Aligning large language models (LLM) with human preference plays a key role in building
modern generative models and can be achieved by reinforcement learning from human …
modern generative models and can be achieved by reinforcement learning from human …