torchrl_mcts

This is a proof of concept on how MCTS can be implemented on top of TorchRL

Resources

1. A Simple Alpha(Go) Zero Tutorial - Stanford
2. Stanford CS234: Reinforcement Learning | Winter 2019 | Lecture 16 - Monte Carlo Tree Search
3. Monte-Carlo Tree Search (MCTS) - Tim Miller
4. Alpha Zero General - Github
5. David Silver: Simulation-Based Search - Youtube
6. Silver, David, Richard S. Sutton, and Martin Müller. "Temporal-difference search in computer Go."
7. AlphaGo Papers:
   1. Mastering the game of Go with deep neural networks and tree search
8. AlphaZero Papers:
   1. A general reinforcement learning algorithm that masters chess, shogi and Go through self-play
      1. Supplementary Material (pdf, zip)
   2. Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
9. MuZero Papers:
   1. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model