Teaching AI agents ethical values using reinforcement learning and policy orchestration.
Ritesh NoothigattuDjallel BouneffoufNicholas MatteiRachita ChandraPiyush MadanKush R. VarshneyMurray CampbellMoninder SinghFrancesca RossiPublished in: IBM J. Res. Dev. (2019)
Keyphrases
- reinforcement learning
- action selection
- agent receives
- multi agent
- optimal policy
- sequential decision making
- multi agent systems
- agent learns
- learning agents
- policy search
- artificial intelligence
- learning process
- software agents
- autonomous agents
- multi agent reinforcement learning
- multi agent environments
- multiagent systems
- multiple agents
- single agent
- markov decision process
- expert systems
- intelligent agents
- machine learning
- decision making
- learning capabilities
- reward function
- web services
- higher education
- reinforcement learning problems
- function approximation
- reinforcement learning algorithms
- action space
- learning environment
- multiagent reinforcement learning
- intelligent behavior
- mobile agents
- control policy
- function approximators
- learning agent
- partially observable environments
- robocup soccer
- learning algorithm
- cooperative
- reinforcement learning agents
- technology enhanced learning
- online learning
- intelligent systems
- multiagent learning
- policy evaluation
- resource allocation
- temporal difference
- state space
- policy gradient
- dynamic environments
- markov decision problems
- state and action spaces
- decision problems
- coalition formation