Submodular Reinforcement Learning.
Manish PrajapatMojmir MutnyMelanie N. ZeilingerAndreas KrausePublished in: ICLR (2024)
Keyphrases
- reinforcement learning
- function approximation
- greedy algorithm
- reinforcement learning algorithms
- model free
- objective function
- multi agent
- state space
- control problems
- dynamic programming
- markov decision processes
- optimal control
- high order
- learning process
- reinforcement learning methods
- learning agent
- markov decision process
- temporal difference learning
- real time
- temporal difference
- action selection
- pairwise
- machine learning