activity
20202023
most citedSpecializing Versatile Skill Libraries using Local Mixture of Experts

3 citations · 7 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20233 cited

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Gen Li, Wenhao Zhan, Jason D. Lee +2

This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes access to both an offline dataset and online interactions with the unknown environment.…

cs.LG2023

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Laixi Shi, Gen Li, Yuting Wei +3

This paper investigates model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision…

cs.LG2023

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

Xiang Ji, Gen Li

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting.…

cs.LG2023

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning

Gen Li, Yuling Yan, Yuxin Chen +1

This paper studies reward-agnostic exploration in reinforcement learning (RL) -- a scenario where the learner is unware of the reward functions during the exploration stage -- and…

cs.LG2022

The Efficacy of Pessimism in Asynchronous Q-Learning

Yuling Yan, Gen Li, Yuxin Chen +1

This paper is concerned with the asynchronous form of Q-learning, which applies a stochastic approximation scheme to Markovian data samples. Motivated by the recent advances in off…

cs.LG20223 cited

Specializing Versatile Skill Libraries using Local Mixture of Experts

Onur Celik, Dongzhuoran Zhou, Ge Li +2

A long-cherished vision in robotics is to equip robots with skills that match the versatility and precision of humans. For example, when playing table tennis, a robot should be cap…