Discovering Intrinsic Reward with Contrastive Random Walk.

Zixuan Pan Zihao Wei Yidong Huang Aditya Gupta

Published in: CoRR (2022)

Keyphrases

random walk
markov chain
directed graph
reinforcement learning
link prediction
transition probabilities
long run
spectral methods
flow graph
markov random walk
stationary distribution
link analysis
graph laplacian
random walker
transition probability matrix