1 result found Sort:

hr0nix
omega hr0nix
4
36
gpl-3.0
5
A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environments.
jax flax mcts rlax muzero nethack minihack model-based-rl reinforcement-learning model-based-reinforcement-learning
Created 2021-06-17
144 commits to main branch, last one about a year ago