Randomized Linear Programming for Tabular Average-Cost Multi-agent Reinforcement Learning.
Alec KoppelAmrit Singh BediBhargav GangulyVaneet AggarwalPublished in: ACSCC (2021)
Keyphrases
- average cost
- multi agent reinforcement learning
- linear programming
- linear program
- multi agent
- dynamic programming
- mathematical programming
- multi agent systems
- multi agent learning
- markov decision chains
- learning agents
- reinforcement learning
- initial state
- np hard
- control policy
- markov decision processes
- stochastic games
- objective function
- optimal solution
- finite state
- finite horizon
- resource allocation
- optimal policy
- finite number
- long run
- distributed control
- artificial intelligence