Forward-Looking and Backward-Looking Responsibility Attribution in Multi-Agent Sequential Decision Making.
Stelios TriantafyllouPublished in: AAMAS (2023)
Keyphrases
- sequential decision making
- multi agent
- reinforcement learning
- interactive dynamic influence diagrams
- decision problems
- influence diagrams
- temporal difference
- multi agent systems
- cooperative
- function approximation
- state space
- learning algorithm
- model free
- artificial intelligence
- supervised learning
- multiple agents
- markov decision processes
- cost function
- expected utility
- reinforcement learning algorithms
- neural network
- decision making