Picture for Jianxiong Li

Jianxiong Li

Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning

Add code
Oct 02, 2024
Viaarxiv icon

xTED: Cross-Domain Policy Adaptation via Diffusion-Based Trajectory Editing

Add code
Sep 13, 2024
Viaarxiv icon

Instruction-Guided Visual Masking

Add code
May 30, 2024
Figure 1 for Instruction-Guided Visual Masking
Figure 2 for Instruction-Guided Visual Masking
Figure 3 for Instruction-Guided Visual Masking
Figure 4 for Instruction-Guided Visual Masking
Viaarxiv icon

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning

Add code
Feb 28, 2024
Viaarxiv icon

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model

Add code
Jan 19, 2024
Viaarxiv icon

A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning

Add code
Nov 27, 2023
Viaarxiv icon

Query-Policy Misalignment in Preference-Based Reinforcement Learning

Add code
May 27, 2023
Viaarxiv icon

PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning

Add code
May 25, 2023
Viaarxiv icon

Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization

Add code
Mar 28, 2023
Viaarxiv icon

Mind the Gap: Offline Policy Optimization for Imperfect Rewards

Add code
Feb 03, 2023
Viaarxiv icon