Reinforcement Learning in Low-Rank MDPs with Density Features

no code implementations • 4 Feb 2023 • Audrey Huang, Jinglin Chen, Nan Jiang

As a central technical challenge, the additive error of occupancy estimation is incompatible with the multiplicative definition of data coverage.

reinforcement-learning Reinforcement Learning (RL) +1

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

no code implementations • 21 Jun 2022 • Jinglin Chen, Aditya Modi, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal

We study reward-free reinforcement learning (RL) under general non-linear function approximation, and establish sample efficiency and hardness results under various standard structural assumptions.

Reinforcement Learning (RL)

Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps

no code implementations • 25 Mar 2022 • Jinglin Chen, Nan Jiang

We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function approximators.

Offline RL Reinforcement Learning (RL)

Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality

no code implementations • ICLR 2022 • Jiawei Huang, Jinglin Chen, Li Zhao, Tao Qin, Nan Jiang, Tie-Yan Liu

Deployment efficiency is an important criterion for many real-world applications of reinforcement learning (RL).

reinforcement-learning Reinforcement Learning (RL)

Model-free Representation Learning and Exploration in Low-rank MDPs

no code implementations • 14 Feb 2021 • Aditya Modi, Jinglin Chen, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal

In this work, we present the first model-free representation learning algorithms for low rank MDPs.

Reinforcement Learning (RL) Representation Learning

Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration

no code implementations • 23 Oct 2020 • Priyank Agrawal, Jinglin Chen, Nan Jiang

This paper studies regret minimization with randomized value functions in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL) +1

Nonstationary Reinforcement Learning with Linear Function Approximation

no code implementations • 8 Oct 2020 • Huozhi Zhou, Jinglin Chen, Lav R. Varshney, Ashish Jagmohan

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment.

reinforcement-learning Reinforcement Learning (RL)

Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusion

no code implementations • ICLR 2019 • Yi Chen, Jinglin Chen, Jing Dong, Jian Peng, Zhaoran Wang

To attain the advantages of both regimes, we propose to use replica exchange, which swaps between two Langevin diffusions with different temperatures.

Information-Theoretic Considerations in Batch Reinforcement Learning

no code implementations • 1 May 2019 • Jinglin Chen, Nan Jiang

Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL).

reinforcement-learning Reinforcement Learning (RL)

Efficient Localized Inference for Large Graphical Models

no code implementations • 28 Oct 2017 • Jinglin Chen, Jian Peng, Qiang Liu

We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property.