265 citations · 489 across the 6 of their papers we have counts for
6 papers · 1 filter
Step-size Optimization for Continual Learning
Thomas Degris, Khurram Javed, Arsalan Sharifnassab +2
In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neu…
Meta-descent for Online, Continual Prediction
Andrew Jacobsen, Matthew Schlegel, Cameron Linke +3
This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be consid…
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
Cam Linke, Nadia M. Ady, Martha White +2
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the env…
The Predictron: End-To-End Learning and Planning
David Silver, Hado van Hasselt, Matteo Hessel +8
One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. Th…
Chi-square Tests Driven Method for Learning the Structure of Factored MDPs
Thomas Degris, Olivier Sigaud, Pierre-Henri Wuillemin
SDYNA is a general framework designed to address large stochastic reinforcement learning problems. Unlike previous model based methods in FMDPs, it incrementally learns the structu…
Off-Policy Actor-Critic
Thomas Degris, Martha White, Richard S. Sutton
This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearl…