Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning.
Harshad KhadilkarHardik MeisheriPublished in: COMAD/CODS (2023)
Keyphrases
- causal relationships
- reinforcement learning
- bayesian networks
- causal discovery
- causal models
- previously unknown
- data mining
- causal structure
- data sets
- causal relations
- function approximation
- causal networks
- neural network
- structural model
- markov decision processes
- optimal policy
- linear models
- latent variables
- state space
- dynamic programming
- training set
- machine learning
- structural models
- search space
- lower bound
- learning algorithm
- real world
- causal effects
- structural descriptions