Motif
Obtain intrinsic motivation from AI feedback
CommonProductProductivityArtificial IntelligenceReinforcement Learning
Motif is a PyTorch-based project that trains AI agents to play NetHack by deriving a reward function from the preferences of a Large Language Model (LLM). It can generate behavior that aligns with human intuition and can be guided through prompt modifications.
Motif Visit Over Time
Monthly Visits
488643166
Bounce Rate
37.28%
Page per Visit
5.7
Visit Duration
00:06:37