Dheevatsa Mudigere

distributed training (2) deep reinforcement learning (1) reinforcement learning (1) sample efficiency (1) ensemble learning (1) distributed learning (1) policy learning (1) neural network optimization (1) empirical risk minimization (1) continuous control (1) alternating optimization (1) communication efficiency (1) quasi-newton method (1) ensemble method (1) model training (1) policy ensemble (1) hierarchical search (1) parallelization strategy (1) remote direct memory access (1) reinforcement learning policy (1)