Seohong Park's banner
Seohong Park's profile picture

Seohong Park

@seohong_park • 4,784 subscribers

Reinforcement Learning | CS Ph.D. Student @berkeley_ai | Physical Intelligence

Shorts

D4RL is a great benchmark, but is saturated. Introducing OGBench, a new benchmark for offline goal-conditioned RL and offline RL! Tasks include HumanoidMaze, Puzzle, Drawing, and more 🙂 Project page: GitHub: 🧵↓

D4RL is a great benchmark, but is saturated. Introducing OGBench, a new benchmark for offline goal-conditioned RL and offline RL! Tasks include HumanoidMaze, Puzzle, Drawing, and more 🙂 Project page: GitHub: 🧵↓

36,410 views