Author

J. Bagnell

h-index 69 View on Semantic Scholar

We have 1 of 234 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Tail-Likelihood Reinforcement Learning

Tail-Likelihood Reinforcement Learning (TailRL), which maximizes the log-probability of exceeding a randomly chosen reward threshold, which gives more weight to rare, high-reward rollouts and can be interpreted as a mixture of Best-of-k gradients.

Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar et al. · 2 citations