On the hardness of finding symmetries in Markov decision processes.
Shravan Matthur NarayanamurthyBalaraman RavindranPublished in: ICML (2008)
Keyphrases
- markov decision processes
- real time dynamic programming
- finite state
- state space
- transition matrices
- reinforcement learning
- optimal policy
- decision theoretic planning
- dynamic programming
- average reward
- decision processes
- average cost
- policy iteration
- finite horizon
- factored mdps
- planning under uncertainty
- reachability analysis
- reinforcement learning algorithms
- model based reinforcement learning
- risk sensitive
- semi markov decision processes
- markov decision process
- collaborative filtering
- np hard
- search space
- computational complexity
- search algorithm
- multi agent