182 citations · 924 across the 64 of their papers we have counts for
3 papers · 1 filter
Value-aware Importance Weighting for Off-policy Reinforcement Learning
Kristopher De Asis, Eric Graves, Richard S. Sutton
Importance sampling is a central idea underlying off-policy prediction in reinforcement learning. It provides a strategy for re-weighting samples from a distribution to obtain unbi…
Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
Khurram Javed, Haseeb Shah, Rich Sutton +1
Constructing states from sequences of observations is an important component of reinforcement learning agents. One solution for state construction is to use recurrent neural networ…
Toward Efficient Gradient-Based Value Estimation
Arsalan Sharifnassab, Richard Sutton
Gradient-based methods for value estimation in reinforcement learning have favorable stability properties, but they are typically much slower than Temporal Difference (TD) learning…