Lipeng Wan

multi-agent reinforcement learning (4) adversarial learning (1) offline reinforcement learning (1) sim-to-real transfer (1) autoregressive generation (1) message passing (1) generative model (1) world model (1) exploration strategy (1) q-value function (1) intrinsic reward (1) causal transformer (1) language guidance (1) directed acyclic graph (1) experience replay (1) value decomposition (1) robot skill (1) transformer model (1) optimal coordination (1) relative overgeneralization (1)