1 citations · 1 across the 6 of their papers we have counts for
6 papers · 1 filter
Should Models Be Accurate?
Esra'a Saleh, John D. Martin, Anna Koop +2
Model-based Reinforcement Learning (MBRL) holds promise for data-efficiency by planning with model-generated experience in addition to learning with experience from the environment…
Adapting the Function Approximation Architecture in Online Reinforcement Learning
John D. Martin, Joseph Modayil
The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimizat…
On Catastrophic Interference in Atari 2600 Games
William Fedus, Dibya Ghosh, John D. Martin +3
Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interference within an environment inhibits le…
Stochastically Dominant Distributional Reinforcement Learning
John D. Martin, Michal Lyskawinski, Xiaohu Li +1
We describe a new approach for managing aleatoric uncertainty in the Reinforcement Learning (RL) paradigm. Instead of selecting actions according to a single statistic, we propose…
Recursive Sparse Pseudo-input Gaussian Process SARSA
John Martin, Brendan Englot
The class of Gaussian Process (GP) methods for Temporal Difference learning has shown promise for data-efficient model-free Reinforcement Learning. In this paper, we consider a rec…
Sparse Gaussian Process Temporal Difference Learning for Marine Robot Navigation
John Martin, Jinkun Wang, Brendan Englot
We present a method for Temporal Difference (TD) learning that addresses several challenges faced by robots learning to navigate in a marine environment. For improved data efficien…