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
- reinforcement learning
- optimal policy
- data visualization
- finite state
- state space
- interactive visual
- policy iteration
- transition matrices
- dynamic programming
- information visualization
- reachability analysis
- decision theoretic planning
- average reward
- action space
- infinite horizon
- markov decision process
- action sets
- state and action spaces
- average cost
- model based reinforcement learning
- decision making
- planning under uncertainty
- finite horizon
- decision problems
- partially observable
- multidimensional data
- convergence rate
- user interface
- information retrieval