Solving Relational MDPs with Exogenous Events and Additive Rewards.
Saket JoshiRoni KhardonPrasad TadepalliAswin RaghavanAlan FernPublished in: CoRR (2013)
Keyphrases
- markov decision processes
- reinforcement learning
- semi markov decision processes
- transition matrices
- markov decision problems
- reward function
- factored mdps
- algebraic decision diagrams
- relational databases
- decision diagrams
- optimal policy
- state space
- event detection
- sequential decision making problems
- finite state
- decision theoretic planning
- human activities
- average cost
- data model
- dynamic programming
- learning algorithm
- state and action spaces
- planning under uncertainty
- average reward
- event sequences
- markov decision process
- partially observable
- reinforcement learning algorithms