Open aletote opened 5 years ago
Hi aletote, you can use any function that is suitable for the DepthPrunedAgent: it should just take a GameState argument, and return a score indicating how good the state is from the perspective of the next player to paly. For example, you can copy the capture_diff
function from pruned_go.py
.
I just pushed an update to the chatper_4 branch including an example interactive program, see here: https://github.com/maxpumperla/deep_learning_and_the_game_of_go/blob/chapter_4/code/alpha_beta_go.py It plays on a 5x5 board cause the implementation is fairly slow.
I would like to test it out but how do I replace the random bot with it in human_v_bot.py?
When I want to call it I dont know what to pass as eval_fn argument.