Xuguang Lan

multi-agent reinforcement learning (4) reinforcement learning (1) semantic embedding (1) offline reinforcement learning (1) sim-to-real transfer (1) policy gradient (1) object detection (1) autoregressive generation (1) visual grounding (1) message passing (1) pomdp planning (1) approximate nearest neighbor (1) robot manipulation (1) generative model (1) adversarial learning (1) world model (1) exploration strategy (1) sparse reward (1) hindsight experience replay (1) deep reinforcement learning (1)