Improved Strong Worst-case Upper Bounds for MDP Planning.
Anchit GuptaShivaram KalyanakrishnanPublished in: IJCAI (2017)
Keyphrases
- upper bound
- worst case
- lower bound
- average case
- planning under uncertainty
- tight bounds
- markov decision processes
- heuristic search
- sample size
- greedy algorithm
- upper and lower bounds
- lower and upper bounds
- state space
- markov decision process
- concept classes
- partially observable
- np hard
- planning under partial observability
- vc dimension
- optimal policy
- decision theoretic
- sample complexity
- space complexity
- approximation algorithms
- error bounds
- initial state
- linear program
- domain independent
- markov decision problems
- partial observability
- decision theoretic planning
- reinforcement learning