10 citations · 46 across the 14 of their papers we have counts for
14 papers
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
Liyuan Mao, Haoran Xu, Xianyuan Zhan +2
One important property of DIstribution Correction Estimation (DICE) methods is that the solution is the optimal stationary distribution ratio between the optimized and data collect…
ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
Liyuan Mao, Haoran Xu, Weinan Zhang +1
In this study, we investigate the DIstribution Correction Estimation (DICE) methods, an important line of work in offline reinforcement learning (RL) and imitation learning (IL). D…
Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization
Xiangsen Wang, Haoran Xu, Yinan Zheng +1
Offline reinforcement learning (RL) has received considerable attention in recent years due to its attractive capability of learning policies from offline datasets without environm…
Offline Reinforcement Learning with Imbalanced Datasets
Li Jiang, Sijie Cheng, Jielin Qiu +3
The prevalent use of benchmarks in current offline reinforcement learning (RL) research has led to a neglect of the imbalance of real-world dataset distributions in the development…
PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning
Jianxiong Li, Xiao Hu, Haoran Xu +3
Offline-to-online reinforcement learning (RL), by combining the benefits of offline pretraining and online finetuning, promises enhanced sample efficiency and policy performance. H…
Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization
Haoran Xu, Li Jiang, Jianxiong Li +4
Most offline reinforcement learning (RL) methods suffer from the trade-off between improving the policy to surpass the behavior policy and constraining the policy to limit the devi…
Mind the Gap: Offline Policy Optimization for Imperfect Rewards
Jianxiong Li, Xiao Hu, Haoran Xu +4
Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to des…
A Policy-Guided Imitation Approach for Offline Reinforcement Learning
Haoran Xu, Li Jiang, Jianxiong Li +1
Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution…
Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations
Haoran Xu, Xianyuan Zhan, Honglei Yin +1
We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead,…
Discriminator-Guided Model-Based Offline Imitation Learning
Wenjia Zhang, Haoran Xu, Haoyi Niu +5
Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from sev…
When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
Jianxiong Li, Xianyuan Zhan, Haoran Xu +3
In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas. Unfortunately, exi…
Constraints Penalized Q-learning for Safe Offline Reinforcement Learning
Haoran Xu, Xianyuan Zhan, Xiangyu Zhu
We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offli…
Model-Based Offline Planning with Trajectory Pruning
Xianyuan Zhan, Xiangyu Zhu, Haoran Xu
The recent offline reinforcement learning (RL) studies have achieved much progress to make RL usable in real-world systems by learning policies from pre-collected datasets without…
DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning
Xianyuan Zhan, Haoran Xu, Yue Zhang +3
Optimizing the combustion efficiency of a thermal power generating unit (TPGU) is a highly challenging and critical task in the energy industry. We develop a new data-driven AI sys…