5 papers
Lyapunov Exponents for Diversity in Differentiable Games
Jonathan Lorraine, Paul Vicol, Jack Parker-Holder +3
Ridge Rider (RR) is an algorithm for finding diverse solutions to optimization problems by following eigenvectors of the Hessian ("ridges"). RR is designed for conservative gradien…
Towards an Understanding of Default Policies in Multitask Policy Optimization
Ted Moskovitz, Michael Arbel, Jack Parker-Holder +1
Much of the recent success of deep reinforcement learning has been driven by regularized policy optimization (RPO) algorithms with strong performance across multiple domains. In th…
Same State, Different Task: Continual Reinforcement Learning without Interference
Samuel Kessler, Jack Parker-Holder, Philip Ball +2
Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL i…
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder +8
In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate t…
Towards Tractable Optimism in Model-Based Reinforcement Learning
Aldo Pacchiano, Philip J. Ball, Jack Parker-Holder +2
The principle of optimism in the face of uncertainty is prevalent throughout sequential decision making problems such as multi-armed bandits and reinforcement learning (RL). To be…