HLG: Bridging Human Heuristic Knowledge and Deep Reinforcement Learning for Optimal Agent Performance.
Bin ChenZehong CaoPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- dynamic programming
- multi agent
- optimal solution
- human users
- optimal control
- domain knowledge
- intelligent agents
- multi agent systems
- software agents
- human experts
- domain experts
- action selection
- expert systems
- knowledge base
- multiple agents
- exhaustive search
- control policy
- artificial agents
- learning algorithm
- multiagent systems
- knowledge acquisition
- knowledge management
- worst case
- decision making
- autonomous agents
- state space
- np hard
- reward function
- reasoning process
- markov decision process
- machine learning
- incomplete knowledge