2 citations · 4 across the 4 of their papers we have counts for
4 papers · 1 filter
Improved POMDP Tree Search Planning with Prioritized Action Branching
John Mern, Anil Yildiz, Larry Bush +2
Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. This paper proposes a method called PA-POMCPOW to sa…
Towards Recurrent Autoregressive Flow Models
John Mern, Peter Morales, Mykel J. Kochenderfer
Stochastic processes generated by non-stationary distributions are difficult to represent with conventional models such as Gaussian processes. This work presents Recurrent Autoregr…
Exchangeable Input Representations for Reinforcement Learning
John Mern, Dorsa Sadigh, Mykel J. Kochenderfer
Poor sample efficiency is a major limitation of deep reinforcement learning in many domains. This work presents an attention-based method to project neural network inputs into an e…
Object Exchangeability in Reinforcement Learning: Extended Abstract
John Mern, Dorsa Sadigh, Mykel Kochenderfer
Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations ca…