Optimal Policies in two-Step Binary Games under Social pressure and Limited Resources.
Paolo PellizzariElena SartoriMarco TolottiPublished in: Adv. Complex Syst. (2015)
Keyphrases
- limited resources
- optimal policy
- markov decision processes
- state space
- reinforcement learning
- processing power
- decision problems
- finite horizon
- multistage
- long run
- dynamic programming
- infinite horizon
- finite state
- resource limitations
- average reward
- policy iteration
- state dependent
- dynamic programming algorithms
- game playing
- average reward reinforcement learning
- markov decision process
- sufficient conditions
- serial inventory systems
- semi markov decision processes
- markov decision problems
- control policies
- partially observable markov decision processes
- initial state