21 citations · 149 across the 34 of their papers we have counts for
7 papers · 1 filter
The Barbados 2018 List of Open Issues in Continual Learning
Tom Schaul, Hado van Hasselt, Joseph Modayil +7
We want to make progress toward artificial general intelligence, namely general-purpose agents that autonomously learn how to competently act in complex environments. The purpose o…
Online Off-policy Prediction
Sina Ghiassian, Andrew Patterson, Martha White +2
This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agen…
Context-Dependent Upper-Confidence Bounds for Directed Exploration
Raksha Kumaraswamy, Matthew Schlegel, Adam White +1
Directed exploration strategies for reinforcement learning are critical for learning an optimal policy in a minimal number of interactions with the environment. Many algorithms use…
Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
Samuel Neumann, Sungsu Lim, Ajin Joseph +3
Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to th…
General Value Function Networks
Matthew Schlegel, Andrew Jacobsen, Zaheer Abbas +3
State construction is important for learning in partially observable environments. A general purpose strategy for state construction is to learn the state update using a Recurrent…
Organizing Experience: A Deeper Look at Replay Mechanisms for Sample-based Planning in Continuous State Domains
Yangchen Pan, Muhammad Zaheer, Adam White +2
Model-based strategies for control are critical to obtain sample efficient learning. Dyna is a planning paradigm that naturally interleaves learning and planning, by simulating one…
Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods
Craig Sherstan, Brendan Bennett, Kenny Young +4
This paper investigates estimating the variance of a temporal-difference learning agent's update target. Most reinforcement learning methods use an estimate of the value function,…