Performance Assessment of Reinforcement Learning Policies for Battery Lifetime Extension in Mobile Multi-RAT LPWAN Scenarios.
Martin StusekPavel MasekDmitri MoltchanovNikita StepanovJiri HosekYevgeni KoucheryavyPublished in: IEEE Internet Things J. (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- management policies
- state space
- reward function
- markov decision process
- control policies
- mobile phone
- hierarchical reinforcement learning
- markov decision processes
- decision problems
- learning process
- decentralized control
- mobile devices
- real world
- partially observable
- battery powered
- life span
- control policy
- partially observable markov decision processes
- learning algorithm
- mobile environments
- model free
- smart phones
- mobile technologies
- function approximation
- energy consumption
- reinforcement learning algorithms
- mobile computing
- optimal control
- markov decision problems
- continuous state
- learning scenarios
- dynamical systems
- multiagent reinforcement learning
- dynamic programming
- wireless sensor networks