Understanding Self-Predictive Learning for Reinforcement Learning.
Yunhao TangZhaohan Daniel GuoPierre Harvey RichemondBernardo Ávila PiresYash ChandakRémi MunosMark RowlandMohammad Gheshlaghi AzarCharline Le LanClare LyleAndrás GyörgyShantanu ThakoorWill DabneyBilal PiotDaniele CalandrielloMichal ValkoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- learning systems
- learning tasks
- state space
- knowledge acquisition
- active learning
- bayesian networks
- partially observable environments
- learning agents
- subject matter
- active exploration
- learning capabilities
- machine learning
- reinforcement learning algorithms
- solving problems
- markov decision processes
- unsupervised learning
- online learning
- learning environment
- multi agent