Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning.
Sumedh A. SontakkeArash MehrjouLaurent IttiBernhard SchölkopfPublished in: ICML (2021)
Keyphrases
- learning agents
- reinforcement learning
- learning process
- learning algorithm
- multi agent
- causal structure
- qualitative models
- action selection
- causal relationships
- automatically discovering
- multi agent systems
- learning agent
- software agents
- reinforcement learning agents
- learned knowledge
- autonomous agents
- multiagent systems
- online learning
- function approximation
- causal models
- resource allocation
- learning mechanism
- single agent
- intelligent agents
- dynamic environments
- supervised learning
- cooperative
- bayesian networks