187 citations · 200 across the 4 of their papers we have counts for
4 papers
Hybrid Reward Architecture for Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Joshua Romoff +3
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dime…
Taking all positive eigenvectors is suboptimal in classical multidimensional scaling
Jeffrey Tsang, Rajesh Pereira
It is hard to overstate the importance of multidimensional scaling as an analysis technique in the broad sciences. Classical, or Torgerson multidimensional scaling is one of the ma…
The parametrized probabilistic finite-state transducer probe game player fingerprint model
Jeffrey Tsang
Fingerprinting operators generate functional signatures of game players and are useful for their automated analysis independent of representation or encoding. The theory for a fing…
N derivatives are necessary for order N+1 convergence in quadrature: a converse result
Jeffrey Tsang
Results on the error bounds of quadrature methods are well known - most state that if the method has degree N, and the integrand has N derivatives, then the error is order N+1. We…