Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy.
Zhihan LiuMiao LuZhaoran WangMichael I. JordanZhuoran YangPublished in: ICML (2022)
Keyphrases
- reinforcement learning
- markov chain
- function approximation
- state space
- learning algorithm
- optimal policy
- markov decision processes
- robotic control
- information exchange
- sustainable development
- low carbon
- policy search
- semi markov
- temporal difference learning
- markov process
- reinforcement learning algorithms
- markov model
- multi agent
- objective function
- model free
- markov decision process
- learning problems
- supervised learning
- data sets
- learning classifier systems
- action space
- function approximators
- exchange information
- optimal control