A Black Swan Hypothesis in Markov Decision Process via Irrationality.
Hyunin LeeDavid AbelMing JinJavad LavaeiSomayeh SojoudiPublished in: CoRR (2024)
Keyphrases
- markov decision process
- state space
- optimal policy
- markov decision processes
- reinforcement learning
- infinite horizon
- finite horizon
- partial observability
- temporal difference learning
- policy iteration
- transition matrices
- initial state
- reward function
- partially observable markov decision processes
- average cost
- transition probabilities
- finite state
- markov chain
- hidden markov models
- search space