Search papers, labs, and topics across Lattice.
Purdue University, West Lafayette, IN, USA
3
0
5
Regularizing the SAIL objective with reverse KL divergence not only resolves convergence issues but also enhances performance in LLM alignment tasks.
Learning policies from just one trajectory in average-reward MDPs is now feasible, with guarantees that could transform how we approach sample efficiency in reinforcement learning.
Achieving near-optimal regret in continuous dueling bandits is now possible with just logarithmic space complexity, opening the door to efficient exploration in complex comparative decision-making problems.
