Generalized circle agent for geometry friends using deep reinforcement learning.
Azmi Can OzgenMandana FasounakiHazim Kemal EkenelPublished in: SIU (2018)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- learning agent
- multi agent systems
- three dimensional
- learning agents
- state action
- intelligent agents
- multiagent systems
- autonomous learning
- reward function
- reinforcement learning agents
- multi agent environments
- learning capabilities
- state abstraction
- agent receives
- function approximation
- dual space
- exploration strategy
- agent architecture
- markov decision processes
- autonomous agents
- state space
- single agent
- mobile agents
- action space
- decision making
- multiagent reinforcement learning
- temporal difference
- dynamic environments
- agent model
- multi agent reinforcement learning
- learning algorithm
- reward shaping
- agent learns
- agent technology
- geometric structure
- multi agent learning
- artificial agents
- decision theoretic
- pedagogical agents
- machine learning
- partially observable
- multiple agents
- software agents
- mobile robot
- learning process
- markov decision process
- agent systems
- robocup soccer
- belief state