Model-Based Reinforcement Learning (RL) is widely believed to have the
p...
Value iteration (VI) is a foundational dynamic programming method, impor...
Training neural networks with discrete stochastic variables presents a u...
We present Hindsight Network Credit Assignment (HNCA), a novel learning
...
Despite empirical success, the theory of reinforcement learning (RL) wit...
Hindsight Credit Assignment (HCA) refers to a recently proposed family o...
The Arcade Learning Environment (ALE) is a popular platform for evaluati...
Reinforcement learning (RL) has had many successes in both "deep" and
"s...
This paper investigates estimating the variance of a temporal-difference...
We present Solrex,an automated solver for the game of Reverse Hex.Revers...