Course
Reinforcement Learning & Robotics
Systems that act, plan and improve by trial.
Reinforcement learning
- Learning biases in human reinforcement learning
- Model-based vs model-free control (goal-directed vs habitual)
- Do reward cues push us to approach rather than just to act?
- When is it worth stopping to think before acting?
- Can a predictive map explain planning with simple learning?
- Does planning ahead actually earn more reward in lab tasks?
- Are habits chunked action sequences run by a goal-directed boss?
- + 6 more →
Robot learning
- Should newborn robots inherit what their parents learned?
- Can a robot learn from its own lucky accidents?
- How do human-side errors affect a robot learning from brain signals?
- Can a robot learn a driving style from a few human demos?
- Can ordinary people teach a robot a skill just by rating its tries?
- + 2 more →