The curious price of distributional robustness in reinforcement learning with a generative model

L Shi, G Li, Y Wei, Y Chen… - Advances in Neural …, 2024 - proceedings.neurips.cc
This paper investigates model robustness in reinforcement learning (RL) via the framework
of distributionally robust Markov decision processes (RMDPs). Despite recent efforts, the …

Settling the sample complexity of model-based offline reinforcement learning

G Li, L Shi, Y Chen, Y Chi, Y Wei - The Annals of Statistics, 2024 - projecteuclid.org
Settling the sample complexity of model-based offline reinforcement learning Page 1 The
Annals of Statistics 2024, Vol. 52, No. 1, 233–260 https://doi.org/10.1214/23-AOS2342 © …

Distributionally robust model-based offline reinforcement learning with near-optimal sample complexity

L Shi, Y Chi - Journal of Machine Learning Research, 2024 - jmlr.org
This paper concerns the central issues of model robustness and sample efficiency in offline
reinforcement learning (RL), which aims to learn to perform decision making from history …

Breaking the sample size barrier in model-based reinforcement learning with a generative model

G Li, Y Wei, Y Chi, Y Gu… - Advances in neural …, 2020 - proceedings.neurips.cc
We investigate the sample efficiency of reinforcement learning in a $\gamma $-discounted
infinite-horizon Markov decision process (MDP) with state space S and action space A …

Adversarial model for offline reinforcement learning

M Bhardwaj, T **e, B Boots, N Jiang… - Advances in Neural …, 2024 - proceedings.neurips.cc
We propose a novel model-based offline Reinforcement Learning (RL) framework, called
Adversarial Model for Offline Reinforcement Learning (ARMOR), which can robustly learn …

Reinforcement learning with human feedback: Learning dynamic choices via pessimism

Z Li, Z Yang, M Wang - arxiv preprint arxiv:2305.18438, 2023 - arxiv.org
In this paper, we study offline Reinforcement Learning with Human Feedback (RLHF) where
we aim to learn the human's underlying reward and the MDP's optimal policy from a set of …

Near-optimal offline reinforcement learning with linear representation: Leveraging variance information with pessimism

M Yin, Y Duan, M Wang, YX Wang - arxiv preprint arxiv:2203.05804, 2022 - arxiv.org
Offline reinforcement learning, which seeks to utilize offline/historical data to optimize
sequential decision-making strategies, has gained surging prominence in recent studies …

Is Q-learning minimax optimal? a tight sample complexity analysis

G Li, C Cai, Y Chen, Y Wei, Y Chi - Operations Research, 2024 - pubsonline.informs.org
Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP)
in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the …

Nearly minimax optimal offline reinforcement learning with linear function approximation: Single-agent mdp and markov game

W **ong, H Zhong, C Shi, C Shen, L Wang… - arxiv preprint arxiv …, 2022 - arxiv.org
Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-
collected dataset without further interactions with the environment. While various algorithms …

The blessing of heterogeneity in federated q-learning: Linear speedup and beyond

J Woo, G Joshi, Y Chi - International Conference on …, 2023 - proceedings.mlr.press
In this paper, we consider federated Q-learning, which aims to learn an optimal Q-function
by periodically aggregating local Q-estimates trained on local data alone. Focusing on …