Qiyue Yin

multi-agent reinforcement learning (3) text generation (2) reinforcement learning (2) natural language generation (1) parameter sharing (1) neural machine translation (1) policy gradient (1) asynchronous training (1) adversarial training (1) value function (1) action-value function (1) model-based reinforcement learning (1) dynamic parameters (1) reward function (1) error propagation (1) policy learning (1) sample efficiency (1) generative adversarial network (1) language model agent (1) neural network architecture (1)