Point-Based Policy Transformation: Adapting Policy to Changing POMDP Models.
Hanna KurniawatiNicholas M. PatrikalakisPublished in: WAFR (2012)
Keyphrases
- optimal policy
- markov decision process
- model free reinforcement learning
- point based value iteration
- partially observable markov decision processes
- probabilistic model
- machine learning
- model selection
- supply chain
- dynamic programming
- reinforcement learning
- control policies
- sufficient conditions
- dynamic environments
- statistical models
- dynamical systems
- decision problems
- reward function
- partially observable
- markov decision problems
- knowledge base
- neural network