Long-Term Values in Markov Decision Processes, (Co)Algebraically.
Frank M. V. FeysHelle Hvid HansenLawrence S. MossPublished in: CMCS (2018)
Keyphrases
- markov decision processes
- long term
- state space
- optimal policy
- reinforcement learning
- finite state
- dynamic programming
- decision theoretic planning
- policy iteration
- transition matrices
- finite horizon
- reachability analysis
- partially observable
- planning under uncertainty
- risk sensitive
- factored mdps
- action sets
- average reward
- model based reinforcement learning
- reinforcement learning algorithms
- average cost
- decision processes
- infinite horizon
- markov decision process
- multi agent
- semi markov decision processes
- markov decision problems
- reward function