Jianhao Wang

multi-agent reinforcement learning (5) value factorization (2) intrinsic reward (2) offline reinforcement learning (2) motion capture (1) attention mechanism (1) self-supervised learning (1) instruction tuning (1) uncertainty quantification (1) human motion (1) video understanding (1) continuous control (1) model-based reinforcement learning (1) distribution shift (1) graph topology (1) communication efficiency (1) exploration policy (1) polynomial time (1) latent variable model (1) data augmentation (1)