add implementation example of state-of-the-art algorithms

suqi / gym-sandbox

An easy-to-customize gym-based env for Reinforcement Learning

MIT License

4 stars 1 forks source link

Open suqi opened 7 years ago

suqi commented 7 years ago

DQN, PG, DDPG, A3C

suqi commented 7 years ago

Can base on OpenAI universe-starter-agent A3C, and OpenAI baselines DQN

suqi commented 7 years ago

Also TensorForce is a great code architecture.