Thommen Karimpanal George

reinforcement learning (2) reward function (2) transfer learning (1) policy gradient (1) gaussian processes (1) policy learning (1) inverse reinforcement learning (1) gaussian process (1) episodic memory (1) model-based reinforcement learning (1) virtual trust region (1) action-value function (1) successor feature (1) trust region (1) agent modeling (1) hybrid control (1) environment dynamics (1) bounded error (1) multi-agent system (1) trajectory value (1)