Planning to chronicle: Optimal policies for narrative observation of unpredictable events.
Hazhar RahmaniDylan A. ShellJason M. O'KanePublished in: Int. J. Robotics Res. (2023)
Keyphrases
- optimal policy
- markov decision processes
- state space
- partially observable markov decision processes
- initial state
- dynamic programming
- decision problems
- finite horizon
- reinforcement learning
- story generation
- planning problems
- infinite horizon
- heuristic search
- markov decision problems
- multistage
- finite state
- average cost
- long run
- sufficient conditions
- dynamic programming algorithms
- average reward reinforcement learning
- state dependent
- semi markov decision processes
- bayesian reinforcement learning
- serial inventory systems
- policy iteration
- markov decision process
- average reward
- lost sales
- interactive narrative
- inventory control
- control policies
- partially observable
- planning domains
- domain independent
- linear programming
- machine learning
- data mining