A Deep Reinforcement Learning Approach towards Pendulum Swing-up Problem based on TF-Agents.
Yifei BiXinyi ChenCaihui XiaoPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- learning agents
- multi agent systems
- action selection
- multi agent reinforcement learning
- multiagent systems
- learning agent
- multi agent environments
- intelligent agents
- autonomous agents
- function approximation
- multiple agents
- robocup soccer
- single agent
- software agents
- cooperative
- agent receives
- decision making
- co occurrence
- agent architecture
- agent systems
- learning capabilities
- reinforcement learning algorithms
- agent behavior
- multiagent learning
- reinforcement learning agents
- agent model
- state space
- dynamic environments
- optimal policy
- model free
- partial observability
- learning algorithm
- mobile agents
- agent technology
- complex environments
- game theoretic
- multi agent learning
- optimal control
- learned knowledge
- decentralized control
- coalition formation
- machine learning
- partially observable