Chenghe Wang

multi-agent reinforcement learning (3) representation learning (2) off-policy evaluation (1) attention mechanism (1) adversarial training (1) communication efficiency (1) collision avoidance (1) counterfactual prediction (1) task decomposition (1) teammate modeling (1) multi-agent pathfinding (1) robot coordination (1) value function factorization (1) incentive communication (1) communication sparsity (1) environment model learning (1) adversarial weighted empirical risk (1) self-supervised information aggregation (1) message aggregation (1) motion planning (1)