Reading & study notes
Notes
Working notes on topics I am learning about. They are informal, and corrections are welcome.
Meta RL
Different from Non-stationary RL setting, in meta learning we try to solve a series of tasks using the learned knowledge, which is essentially formulated as ‘learning to learn’. For example, in a grid world...
Read noteNon-stationary RL
Non-Stationary RL Usually we consider optimizing an objective under a stationary MDP with a fixed transition and reward function. We can learn the optimal policy through policy evaluation and policy improvement steps. However, in...
Read note