A reinforcement learning approach for the circle agent of geometry friends.
Joao QuiterioRui PradaFrancisco S. MeloPublished in: CIG (2015)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- learning agent
- autonomous learning
- multiagent systems
- reward function
- partially observable
- multi agent systems
- state abstraction
- exploration strategy
- state action
- autonomous agents
- intelligent agents
- multi agent environments
- function approximation
- markov decision process
- single agent
- agent receives
- markov decision processes
- action space
- agent model
- state space
- reinforcement learning agents
- three dimensional
- learning capabilities
- reward shaping
- model free
- learning process
- reinforcement learning algorithms
- software agents
- dynamic programming
- machine learning
- neural network
- robocup soccer
- decision making
- agent architecture
- control policy
- multi agent reinforcement learning
- optimal policy
- decision problems
- agent learns
- learning agents
- geometric constraints
- geometric structure
- decision theoretic
- temporal difference