Towards Interpretable Reinforcement Learning Using Attention Augmented Agents.
Alex MottDaniel ZoranMike ChrzanowskiDaan WierstraDanilo J. RezendePublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- multi agent
- learning agents
- multi agent systems
- multiagent systems
- single agent
- action selection
- multiple agents
- multi agent environments
- intelligent agents
- agent receives
- multiagent learning
- learning agent
- multi agent reinforcement learning
- autonomous agents
- software agents
- partial observability
- cooperative
- multiagent reinforcement learning
- agent behavior
- decision making
- robocup soccer
- learning capabilities
- model free
- machine learning
- agent architecture
- dynamic environments
- incomplete information
- temporal difference
- learning algorithm
- complex environments
- evolutionary learning
- function approximation
- mobile agents
- autonomous mental development
- decision theoretic
- reinforcement learning agents
- learning process
- state space
- learned knowledge
- reinforcement learning algorithms
- markov decision processes
- reinforcement learning methods
- optimal control
- interacting agents
- agent systems
- complex domains
- reward function
- neural network
- coalition formation