The Complexity of Finding an Optimal Policy for Language Convergence.
Kiran LakkarajuLes GasserPublished in: SAB (2006)
Keyphrases
- optimal policy
- decision problems
- markov decision processes
- dynamic programming
- state space
- infinite horizon
- finite state
- reinforcement learning
- finite horizon
- multistage
- long run
- state dependent
- average reward
- serial inventory systems
- markov decision process
- sufficient conditions
- asymptotically optimal
- bayesian reinforcement learning
- policy iteration
- average cost
- initial state
- convergence rate
- computational complexity
- inventory level
- machine learning
- lost sales
- data mining