Search papers, labs, and topics across Lattice.
3
0
3
Action chunking in CRL boosts performance by over 90% in certain environments, revealing that richer temporal representations can significantly enhance learning.
Extracting temporal geometry from generative models can boost reinforcement learning performance by over 2x without changing the optimal policy.
Forget hand-engineered reward functions: this method learns complex exploratory behaviors by simply predicting which states lead to unpredictable futures.
