Agent-Agnostic Human-in-the-Loop Reinforcement Learning.
David AbelJohn SalvatierAndreas StuhlmüllerOwain EvansPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- artificial agents
- multi agent systems
- human users
- multi agent environments
- autonomous learning
- function approximation
- learning agent
- multiagent systems
- intelligent agents
- reward function
- autonomous agents
- partially observable
- single agent
- learning agents
- learning capabilities
- decision making
- agent receives
- machine learning
- temporal difference
- software agents
- mobile agents
- computational models
- human agent
- reinforcement learning agents
- cooperative
- state space
- neural network
- agent architecture
- learning algorithm
- state abstraction
- multi agent reinforcement learning
- dynamic environments
- agent interactions
- optimal policy
- markov decision process
- agent systems
- transfer learning
- human activities