Picture for Sangwoo Shin

Sangwoo Shin

LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble

Add code
Nov 26, 2024
Figure 1 for LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
Figure 2 for LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
Figure 3 for LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
Figure 4 for LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble
Viaarxiv icon

Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments

Add code
Aug 02, 2024
Viaarxiv icon

One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill

Add code
Feb 13, 2024
Viaarxiv icon

SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation

Add code
Feb 12, 2024
Viaarxiv icon