Seoul, South Korea
PreferenceTransformer. Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)
168ARP. Guide Your Agent with Adaptive Multimodal Rewards (NeurIPS 2023 Accepted)
33REDS_agent. Subtask-Aware Visual Reward Learning from Segmented Demonstrations (ICLR 2025 accepted)
19DEAS-Isaac-GR00T. DEAS + Isaac-GR00T + RoboCasa
19DEAS-FQL. DEAS + FQL + OGBench
11REDS_reward_learning. Python
1rlhf_robobase. Robobase + RLHF
1furniture-bench. FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)
1custom_openpi. openpi used for robocasa eval
1 views 9 projects
Apply