Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning.
Hassam Ullah SheikhLadislau BölöniPublished in: CoRR (2019)
Keyphrases
- reward function
- multi objective
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- evolutionary algorithm
- optimal policy
- policy search
- state space
- partially observable
- multiple agents
- multi agent
- function approximation
- inverse reinforcement learning
- markov decision process
- initially unknown
- transition model
- genetic algorithm
- hierarchical reinforcement learning
- objective function
- mobile robot
- transition probabilities
- robotic systems
- real robot
- learning agent
- machine learning
- markov decision problems
- control policies
- state variables
- state action
- learning algorithm
- multi criteria
- autonomous robots
- multi agent systems
- temporal difference
- markov models