Reinforcing Your Learning of Reinforcement Learning

NeurIPS 2019: DQN(λ) = Deep Q-Network + λ-returns.

Official implementation of the paper "Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning Algorithms": https://arxiv.org/abs/1909.01779 To appear at the next NeurIPS2019 DRL-Workshop

Deep Reinforcement Learning agents for OpenAI Gym Atari 2600

Develop an AI player of Atari Skiing with deep reinforcement learning