Lecture Notes on Partially Known MDPs.

Guillermo A. Pérez

Published in: CoRR (2021)

Keyphrases

lecture notes
markov decision processes
computer science
revised selected papers
reinforcement learning
revised papers
factored mdps
finite horizon
state space
planning under uncertainty
machine learning for multimodal interaction

decision theoretic planning
decision diagrams
optimal policy
invited paper
policy iteration
factored markov decision processes
average reward
advances in information retrieval
international symposium
data mining

image computing and computer assisted intervention
summer school
lecture notes in artificial intelligence
information retrieval
markov decision process
databases
real time dynamic programming
probabilistic planning
markov decision problems
average cost

international workshop
user interface
artificial intelligence
initial state
partially observable
planning problems
dynamic programming
semi markov decision processes
decision making
data sets