Hanbo Zhang

reinforcement learning (1) policy gradient (1) object detection (1) in-context learning (1) multimodal learning (1) visual grounding (1) instruction following (1) pomdp planning (1) robot manipulation (1) model training (1) vision language model (1) multimodal large language model (1) sparse reward (1) hindsight experience replay (1) task planning (1) image understanding (1) spatial reasoning (1) partial observation (1) trust region policy optimization (1) embodied navigation (1)