Week 24 - June 22
Wednesday 6/15
- continue deep rl class with unit 2, interesting notebook to learn about using optuna to tune hyperparameters
Friday 6/17
- Sylvain pointed me to a paper from X: Robust Reinforcement Learning with Distributional Risk-averse formulation now in zotero to use distribution information to strengthen RL epxloration. To be read and tested