OpenAI Baselines: DQN
OpenAI Blog
OpenAI released Baselines, a collection of reinforcement learning algorithm implementations designed to match published performance benchmarks. The initial release includes DQN and three variants of the algorithm. The open-source code enables other researchers to reproduce and build upon these baseline implementations.
Why it matters
We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published results. We’ll release the algorithms over upcoming months; today’s release includes DQN and three of its variants.