Closed alexhernandezgarcia closed 10 months ago
This PR implements the detailed balance objective, building upon some of the code developed for the forward-looking loss.
Experiments with the Grid and the Tetris on wandb: https://wandb.ai/alexhg/detailedbalance
This PR implements the detailed balance objective, building upon some of the code developed for the forward-looking loss.
Experiments with the Grid and the Tetris on wandb: https://wandb.ai/alexhg/detailedbalance