57 citations · 230 across the 22 of their papers we have counts for
11 papers · 1 filter
Planning with Expectation Models for Control
Katya Kudashkina, Yi Wan, Abhishek Naik +1
In model-based reinforcement learning (MBRL), Wan et al. (2019) showed conditions under which the environment model could produce the expectation of the next feature vector rather…
Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
Katya Kudashkina, Patrick M. Pilarski, Richard S. Sutton
Intelligent assistants that follow commands or answer simple questions, such as Siri and Google search, are among the most economically important applications of AI. Future convers…
Discounted Reinforcement Learning Is Not an Optimization Problem
Abhishek Naik, Roshan Shariff, Niko Yasui +2
Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. It is not an optimization problem in its usual formulat…
Should All Temporal Difference Learning Use Emphasis?
Xiang Gu, Sina Ghiassian, Richard S. Sutton
Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventi…
Reactive Reinforcement Learning in Asynchronous Environments
Jaden B. Travnik, Kory W. Mathewson, Richard S. Sutton +1
The relationship between a reinforcement learning (RL) agent and an asynchronous environment is often ignored. Frequently used models of the interaction between an agent and its en…
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,…