James Harrison

Robotics (1)

learned optimizer (2) continual learning (2) deep reinforcement learning (1) multi-agent reinforcement learning (1) reinforcement learning (1) human-robot interaction (1) robot perception (1) markov decision process (1) sequential decision making (1) bipartite matching (1) permutation equivariance (1) neural network optimization (1) online learning (1) gradient estimation (1) representation learning (1) online optimization (1) variance reduction (1) off-policy learning (1) off-policy reinforcement learning (1) model compression (1)