OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Role in this project:
ML Engineer Contributions:6 reviews, 23 commits, 3 PRs in 2 years 5 months
Contributions summary:Neil contributed to the development of a single-player PPO (Proximal Policy Optimization) algorithm, including an example implementation and a test. They added a new Atari game environment and adapted existing code for Atari games. The user also made minor updates, such as fixing a typo in a help string and highlighting a subtle feature of the NashConv API.
reinforcement-learninggamesmultiagentcpppython
Contributions:44 commits, 5 pushes in 2 months