Videos 10
1. Deep Q-Learning (13 min)
2. From Policy Gradient to Deep Reinforcement Learning (14 min)
3. Actor-Critic Architecture (10 min)
4. Eligibility traces for Policy-Gradient and Actor-Critic (11 min)
4*. How do eligibility traces arise in Policy-Gradient? (20 min)
5. Three-factor rules (14 min)
5*. Application: Real Brains and Real Tasks (15 min)
6. Application: Learning to find a goal (16 min)
7. Model-based versus Model-free Reinforcement Learning (11 min)
- Contact
- EPFL CH-1015 Lausanne
- +41 21 693 11 11
Follow the pulses of EPFL on social networks
© 2023 EPFL, all rights reserved