turbozero

turbozero copied to clipboard

Batch MCTS is needed !!!

7

The current batch only among multiple games, not one search batched. for example , if one search use 400 simulations, thoese 400 simulations will run one by one, not bacthed.

Nightbringers

AlphaZero+MCTS: Visit probabilities for invalid actions can be non-zero

3

Hey there - I've drafted an implementation of a custom environment for the (approximate) matrix semigroup reachability problem, which I've added to my fork here: https://github.com/bubble-07/turbozero. One thing that's currently...

bubble-07

The key differences between this work and the implementation of alphazero in PGX

1

A great work! Can you tell me the key differences between this work and the implementation of alphazero in PGX: https://github.com/sotetsuk/pgx/tree/main/examples/alphazero, and what are the specific advantages and disadvantages? I...

CDM1619

Single Player Tester

1

This PR proposes a basic implementation of a `SinglePlayerTester` to test agent updates on single player games. The tester compare the `best_params` agent saved in a `SinglePlayerTestState` against a `params`...

xvalcarce

Hi, First, thank you for the fantastic Turbozero repository. It worked perfectly on my laptop CPU when I ran **hello_world.ipynb**. I’m now trying to run Turbozero on our GPU cluster...

fohmij