Comparing Human Behavior to an Optimal Policy for Innovation.
Bonan ZhaoNatalia VélezThomas L. GriffithsPublished in: AAAI Spring Symposia (2024)
Keyphrases
- human behavior
- optimal policy
- markov decision processes
- reinforcement learning
- finite horizon
- long run
- state space
- dynamic programming
- infinite horizon
- decision problems
- state dependent
- daily life
- multistage
- human subjects
- sufficient conditions
- average reward
- markov decision process
- bayesian reinforcement learning
- lost sales
- markov decision problems
- visual attention
- average cost
- control policies
- serial inventory systems
- develop a mathematical model