Facilitating testing and debugging of Markov Decision Processes with interactive visualization.
Sean McGregorHailey BuckinghamThomas G. DietterichRachel HoutmanClaire A. MontgomeryRonald A. MetoyerPublished in: VL/HCC (2015)
Keyphrases
- markov decision processes
- interactive visualization
- data visualization
- state space
- finite state
- interactive visual
- reinforcement learning
- information visualization
- dynamic programming
- optimal policy
- transition matrices
- partially observable
- reachability analysis
- action space
- average cost
- model based reinforcement learning
- policy iteration
- finite horizon
- planning under uncertainty
- decision theoretic planning
- reward function
- average reward
- multidimensional data
- infinite horizon
- markov decision process
- real world
- action sets
- social network analysis