Automatic Itinerary Planning Using Triple-Agent Deep Reinforcement Learning.
Bo-Hao ChenJin HanShengxin ChenJia-Li YinZhaojiong ChenPublished in: IEEE Trans. Intell. Transp. Syst. (2022)
Keyphrases
- reinforcement learning
- action selection
- multi agent
- partially observable
- stochastic domains
- reactive agents
- single agent
- decision theoretic
- multi agent systems
- state space
- intelligent agents
- mobile agents
- reinforcement learning algorithms
- software agents
- agent behavior
- external events
- markov decision process
- learning agents
- state abstraction
- semantic web service composition
- reward shaping
- semi automatic
- action selection mechanism
- optimal policy
- exploration strategy
- multiagent systems
- function approximation
- autonomous learning
- information gathering
- learning agent
- autonomous agents
- plan execution
- machine learning
- learning algorithm
- deterministic domains
- decision making
- heuristic search
- agent technology
- planning problems
- learning capabilities
- reward function
- partially observable markov decision processes
- multiple agents
- agent architecture
- agent model
- agent receives
- plan recognition
- goal directed
- dynamic programming
- model free
- partially observable markov decision process
- incomplete knowledge
- markov decision processes
- state action