Reinforcement Learning for Motion Policies in Mobile Relaying Networks.
Spilios EvmorfosKonstantinos I. DiamantarasAthina P. PetropuluPublished in: IEEE Trans. Signal Process. (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- motion analysis
- image sequences
- mobile devices
- motion estimation
- optical flow
- mobile phone
- social networks
- function approximation
- human motion
- space time
- reward function
- model free
- camera motion
- network structure
- motion planning
- moving objects
- markov decision process
- network connectivity
- wireless technologies
- control policies
- partially observable markov decision processes
- long run
- markov decision problems
- machine learning
- reinforcement learning agents
- policy gradient methods
- fitted q iteration
- mobile applications
- motion field
- markov decision processes
- motion model
- mobile learning
- action selection
- mobile networks
- mobile nodes
- motion capture
- humanoid robot
- optimal control
- multi agent
- multimedia services
- state space
- delay tolerant