7 papers
Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning
Parham Mohammad Panahi, Armin Ashrafi, Haoyu Du +3
Experience replay remains one of the most practical and useful algorithmic tools in the deep reinforcement learning (DRL) toolbox. Aside from the limited success of prioritized rep…
Application-Driven Innovation in Machine Learning
David Rolnick, Alan Aspuru-Guzik, Sara Beery +8
In this position paper, we argue that application-driven research has been systemically under-valued in the machine learning community. As applications of machine learning prolifer…
Position: Lifetime tuning is incompatible with continual reinforcement learning
Golnaz Mesbahi, Parham Mohammad Panahi, Olya Mastikhina +3
In continual RL we want agents capable of never-ending learning, and yet our evaluation methodologies do not reflect this. The standard practice in RL is to assume unfettered acces…
Fine-Tuning without Performance Degradation
Han Wang, Adam White, Martha White
Fine-tuning policies learned offline remains a major challenge in application domains. Monotonic performance improvement during \emph{fine-tuning} is often challenging, as agents t…
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
Jacob Adkins, Michael Bowling, Adam White
The performance of modern reinforcement learning algorithms critically relies on tuning ever-increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lea…
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Esraa Elelimy, Adam White, Michael Bowling +1
Recurrent Neural Networks (RNNs) are used to learn representations in partially observable environments. For agents that learn online and continually interact with the environment,…