Joel Lehman

Reinforcement Learning (1)

deep reinforcement learning (2) reinforcement learning (2) curriculum learning (1) network architecture (1) gradient descent (1) object detection (1) neural architecture search (1) convolutional neural network (1) neural network visualization (1) synthetic data generation (1) policy learning (1) partially observable markov decision process (1) continuous control (1) reward function (1) image generation (1) spatial representation (1) atari game (1) autonomous agent (1) autonomous vehicle (1) representation learning (1)