Search Results for author:
Found 2 papers, 1 papers with code
Loss Dynamics of Temporal Difference Reinforcement Learning
We study how learning dynamics and plateaus depend on feature structure, learning rate, discount factor, and reward function.
Reusability and Transferability of Macro Actions for Reinforcement Learning
However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to bypass intermediate states to a farther state and facilitate its learning procedure.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
