Reinforcement Learning for UAV control with Policy and Reward Shaping.
Cristian Millán-AriasRuben ContrerasFrancisco CruzBruno J. T. FernandesPublished in: CoRR (2022)
Keyphrases
- reward shaping
- reinforcement learning
- control policy
- markov decision problems
- optimal policy
- control policies
- state space
- reinforcement learning algorithms
- action selection
- reward function
- complex domains
- policy search
- unmanned aerial vehicles
- partially observable
- markov decision process
- optimal control
- markov decision processes
- agent learns
- dynamic programming
- model free
- control system
- function approximation
- path planning
- decision problems
- policy iteration
- control strategy
- machine learning
- learning agent
- function approximators
- utility function
- average reward
- transfer learning
- monte carlo
- transition model
- linear programming
- average cost