Optimal Control of Logically Constrained Partially Observable and Multi-Agent Markov Decision Processes.
Krishna Chaitanya KalagarlaDhruva KartikDongming ShenRahul JainAshutosh NayyarPierluigi NuzzoPublished in: CoRR (2023)
Keyphrases
- partially observable
- optimal control
- markov decision processes
- reinforcement learning
- multi agent
- dynamic programming
- infinite horizon
- state space
- control problems
- risk sensitive
- optimal policy
- planning under uncertainty
- policy iteration
- function approximation
- finite state
- markov decision problems
- reward function
- markov decision process
- reinforcement learning algorithms
- average cost
- control strategy
- finite horizon
- model free
- learning algorithm
- multiple agents
- single agent
- average reward
- machine learning
- partially observable markov decision processes
- temporal difference
- state variables
- decision processes
- linear program
- linear programming
- probability distribution
- data mining
- partially observable markov decision process