kingsharaman

RNaD negative loss and barely any correlation of loss with NashConv

7

I am training RNaDSolver on Kuhn Poker with this config: ``` config = rnad.RNaDConfig( game_name="kuhn_poker", trajectory_max=10, state_representation=rnad.StateRepresentation.INFO_SET, policy_network_layers=(128,), batch_size=256, learning_rate=1e-6, seed=42 ) ``` 2 things I cannot explain: 1. There...