mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 19:50:17 +01:00
6d40ad1650
* updating the documentation website * adding the built docs * update of api docstrings across coach and tutorials 0-2 * added some missing api documentation * New Sphinx based documentation
1.1 KiB
1.1 KiB
Actions space: Discrete
References: Distributional Reinforcement Learning with Quantile Regression
Network Structure
Algorithm Description
Training the network
Sample a batch of transitions from the replay buffer.
First, the next state quantiles are predicted. These are used in order to calculate the targets for the network, by following the Bellman equation. Next, the current quantile locations for the current states are predicted, sorted, and used for calculating the quantile midpoints targets.
The network is trained with the quantile regression loss between the resulting quantile locations and the target quantile locations. Only the targets of the actions that were actually taken are updated.
Once in every few thousand steps, weights are copied from the online network to the target network.