Seminars that accompany course CS294 at Berkeley.

1. Intro to RL [presentation] [assignment]
   • Assignment - MNIST PyTorch
   • Example - CartPole Imitation Learning
   • Example - PyTorch Dynamic Batching
2. Imitation learning and policy gradient theorem [presentation]
3. Policy gradient and Actor-Critic algorithm [presentation][assignment]
4. Model-based RL [presentation]
5. Deterministic policy gradient [presentation] and multi-armed bandits [presentation]
6. Inverse RL [presentation]
7. Advanced Policy Gradient [presentation]