Siddhant Jayakumar

reinforcement learning (3) sparse training (2) multi-task learning (2) neural network pruning (2) model compression (2) policy gradient (1) curriculum learning (1) knowledge transfer (1) knowledge distillation (1) policy learning (1) computational efficiency (1) episodic memory (1) gradient descent (1) model pruning (1) entropy regularization (1) task distribution (1) progressive training (1) policy distillation (1) policy representation (1) action-space curriculum (1)