Can Wikipedia Help Offline Reinforcement Learning?
Machel ReidYutaro YamadaShixiang Shane GuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- knowledge base
- wordnet
- semantic relations
- markov decision processes
- real time
- reinforcement learning algorithms
- temporal difference learning
- external knowledge
- state space
- learning algorithm
- reinforcement learning methods
- world knowledge
- entity ranking
- multi agent reinforcement learning
- real robot
- robotic control
- temporal difference
- model free
- named entities
- multi agent
- machine learning
- action selection
- link structure
- learning problems
- transfer learning
- web search
- stochastic approximation
- supervised learning