Vinicius Zambaldi

multi-agent reinforcement learning (3) reinforcement learning (1) policy optimization (1) game theory (1) nash equilibrium (1) multi-agent learning (1) policy selection (1) sequence segmentation (1) partially observable (1) zero-sum game (1) sparse reward (1) partial observation (1) game-theoretic analysis (1) game-theoretic approach (1) common-pool resource (1) compositional imitation learning (1) latent encoding (1) hierarchical agent (1) variable-length segment (1) multi-agent system (1)