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 …
Variance-dependent regret bounds for linear bandits and reinforcement learning: Adaptivity and computational efficiency
Recently, several studies\citep {zhou2021nearly, zhang2021variance, kim2021improved,
zhou2022computationally} have provided variance-dependent regret bounds for linear …
zhou2022computationally} have provided variance-dependent regret bounds for linear …
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 …
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 …
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 …
Federated Q-learning: Linear regret speedup with low communication cost
In this paper, we consider federated reinforcement learning for tabular episodic Markov
Decision Processes (MDP) where, under the coordination of a central server, multiple …
Decision Processes (MDP) where, under the coordination of a central server, multiple …
Horizon-free and instance-dependent regret bounds for reinforcement learning with general function approximation
To tackle long planning horizon problems in reinforcement learning with general function
approximation, we propose the first algorithm, termed as UCRL-WVTR, that achieves …
approximation, we propose the first algorithm, termed as UCRL-WVTR, that achieves …
State-free Reinforcement Learning
In this work, we study the\textit {state-free RL} problem, where the algorithm does not have
the states information before interacting with the environment. Specifically, denote the …
the states information before interacting with the environment. Specifically, denote the …
Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds
Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning
inside the learned model is perhaps the most standard and simplest Model-based …
inside the learned model is perhaps the most standard and simplest Model-based …
Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
In this paper, we consider model-free federated reinforcement learning for tabular episodic
Markov decision processes. Under the coordination of a central server, multiple agents …
Markov decision processes. Under the coordination of a central server, multiple agents …