Ashwin Balakrishna

Reinforcement Learning (1)

imitation learning (4) reinforcement learning (3) cable untangling (2) continuous control (2) robot manipulation (2) policy gradient (1) markov decision process (1) budget-aware learning (1) robotic grasping (1) domain randomization (1) interactive learning (1) mutual information (1) sequential decision making (1) novelty detection (1) demonstration learning (1) generalization ability (1) depth perception (1) reward uncertainty (1) safe reinforcement learning (1) robotic manipulation (1)