OpenAI: Spinning Up in Deep RL

OpenAI has released Spinning Up in Deep RL, an educational resource designed to teach deep reinforcement learning to newcomers. The resource includes a guide on becoming a deep RL researcher, a curated list of key papers organized by topics such as model-free RL, exploration, transfer learning, hierarchy, memory, model-based RL, meta-RL, scaling RL, real-world RL, safety, imitation learning, and reproducibility, along with exercises and benchmarks for implementations.

Welcome to Spinning Up in Deep RL ¶ welcome-to-spinning-up-in-deep-rl Spinning Up as a Deep RL Researcher spinningup/spinningup.html Key Papers in Deep RL spinningup/keypapers.html 1. Model-Free RL spinningup/keypapers.html model-free-rl 2. Exploration spinningup/keypapers.html exploration 3. Transfer and Multitask RL spinningup/keypapers.html transfer-and-multitask-rl 4. Hierarchy spinningup/keypapers.html hierarchy 5. Memory spinningup/keypapers.html memory 6. Model-Based RL spinningup/keypapers.html model-based-rl 7. Meta-RL spinningup/keypapers.html meta-rl 8. Scaling RL spinningup/keypapers.html scaling-rl 9. RL in the Real World spinningup/keypapers.html rl-in-the-real-world 10. Safety spinningup/keypapers.html safety 11. Imitation Learning and Inverse Reinforcement Learning spinningup/keypapers.html imitation-learning-and-inverse-reinforcement-learning 12. Reproducibility, Analysis, and Critique spinningup/keypapers.html reproducibility-analysis-and-critique 13. Bonus: Classic Papers in RL Theory or Review spinningup/keypapers.html bonus-classic-papers-in-rl-theory-or-review Exercises spinningup/exercises.html Benchmarks for Spinning Up Implementations spinningup/bench.html