Active Trajectory Estimation for Partially Observed Markov Decision Processes via Conditional Entropy.
Timothy L. MolloyGirish N. NairPublished in: CoRR (2021)
Keyphrases
- markov decision processes
- partially observed
- conditional entropy
- information theory
- state space
- expected reward
- optimal policy
- transition matrices
- finite state
- mutual information
- decision theoretic planning
- reachability analysis
- policy iteration
- dynamic programming
- planning under uncertainty
- factored mdps
- partially observable
- finite horizon
- risk sensitive
- infinite horizon
- reinforcement learning
- decision processes
- action space
- action sets
- bayes error rate
- stochastic shortest path
- average reward
- reinforcement learning algorithms
- decision problems
- search algorithm
- state abstraction
- state and action spaces
- markov decision process
- discounted reward
- information theoretic
- model checking