Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
Action chunking unlocks temporally interpretable decision trees that match neural network performance with up to 80% fewer parameters.
CURB (Collusion Unwinding via Reward shaping and Belief injection), a reward-shaping framework that penalizes this Total Variation (TV) distance signal during Q-learning and is guaranteed to convert any SPC fixed point of the dynamics into a trivial one, thus precluding collusive equilibria sustained by punishment threats.
Action-only diffusion policies can now satisfy complex human-defined constraints with minimal runtime overhead, achieving 100% task success and drastically reducing violations.
