Visualizing Dynamics: from t-SNE to SEMI-MDPs.

Nir Ben-Zrihem Tom Zahavy Shie Mannor

Published in: CoRR (2016)

Keyphrases

markov decision processes
reinforcement learning
state space
dynamical systems
optimal policy
dynamic programming
dynamic model
interactive visualization
planning under uncertainty
control system
information visualization
policy iteration
highly nonlinear
probabilistic planning
factored mdps