NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions.

In this work, we conduct a comprehensive study of NetHack and examine various learning mechanisms to enhance the performance of neural models.

Modernworksadoptvarious Intrinsic Reward (IR) designstoguideexplorationin hard-explorationsettings. W evaluate AMIGo for 500Msteps12].

Figure dynamics into predict learning from green.

As advocated by [39, 38, 18], procedurally generated environments are a promising direction for testing systematic generalization of RL agents.

Neural policy learning methods have achieved remarkable results in various control problems, ranging from Atari games to simulated locomotion.

NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions.

We support different padding strategies and alphabet sizes, but by default we choose an alphabet size of 96, where the last character is used for padding.