On Jointly Optimizing Partial Offloading and SFC Mapping: A Cooperative Dual-agent Deep Reinforcement Learning Approach.
Xinhan WangHuanlai XingFuhong SongShouxi LuoPenglin DaiBowen ZhaoPublished in: CoRR (2022)
Keyphrases
- cooperative
- multi agent
- reinforcement learning
- multi agent systems
- cooperating agents
- action selection
- multiagent reinforcement learning
- learning agent
- multi agent reinforcement learning
- multi agent environments
- cooperative agents
- multiagent systems
- single agent
- intelligent agents
- interacting agents
- function approximation
- state abstraction
- partial information
- autonomous agents
- multiple agents
- autonomous learning
- reward function
- state space
- decision making
- reinforcement learning algorithms
- agent model
- exploration strategy
- markov decision processes
- reinforcement learning agents
- partially observable
- reward shaping
- dynamic programming
- state action
- learning agents
- learning in multi agent systems
- learning capabilities
- action space
- multiagent learning
- agent systems
- pedagogical agents
- optimal control
- robocup soccer
- optimal policy
- dynamic environments
- exploration exploitation tradeoff
- multi agent learning
- cooperative search
- agent receives
- learning process
- joint action
- software agents
- game theory
- agent architecture
- temporal difference
- learning algorithm