Oak Lab
Research at Oak Lab
Prior research
- The OaK Architecture: A Vision of SuperIntelligence from Experience
- The Big World Hypothesis and its Ramifications for Artificial Intelligence
- SwiftTD: A Fast and Robust Algorithm for Temporal Difference Learning
- Step-size Optimization for Continual Learning
- Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
- Reward-Respecting Subtasks for Model-Based Reinforcement Learning
- The Alberta Plan for AI Research
- Meta-learning Representations for Continual Learning
- Horde: A Scalable Real-Time Architecture for Learning Knowledge from Unsupervised Sensorimotor Interaction
- Adapting Bias by Gradient Descent: An Incremental Version of Delta-Bar-Delta