Approximate Exploitability: Learning a Best Response.
Finbarr TimbersNolan BardEdward LockhartMarc LanctotMartin SchmidNeil BurchJulian SchrittwieserThomas HubertMichael BowlingPublished in: IJCAI (2022)
Keyphrases
- learning process
- online learning
- learning tasks
- learning algorithm
- training data
- reinforcement learning
- supervised learning
- learning phase
- data sets
- cognitive load
- learning scheme
- learning models
- learning analytics
- inductive learning
- incremental learning
- background knowledge
- empirical studies
- knowledge acquisition
- artificial neural networks
- computer vision
- social networks
- search engine