Papers2

#actor-critic

Next Embedding Prediction Makes World Models Stronger

George Bredis, Nikita Balagansky et al.Mar 3arXiv

NE-Dreamer is a model-based reinforcement learning agent that skips rebuilding pixels and instead learns by predicting the next step’s hidden features.

#model-based reinforcement learning#world models#next-embedding prediction

Not triaged yet

Multi-agent cooperation through in-context co-player inference

Intermediate

Marissa A. Weis, Maciej Wołczyk et al.Feb 18arXiv

The paper shows that AI agents can learn to cooperate simply by playing lots of different kinds of opponents and figuring them out on the fly, without hardcoding how those opponents learn.

#multi-agent reinforcement learning#in-context learning#co-player inference

Not triaged yet