Paul Auerbach

Results 4 issues of Paul Auerbach

This PR introduces the Soft Actor Critic for discrete actions (SACD) algorithm. ## Description This PR implements the SAC-Discrete algorithm as described in this paper https://arxiv.org/abs/1910.07207. This implementation borrows code...

Maintainers on vacation

This MR adds the ability to output the current warning and OSSD states the scanner calculates and transmits as part of the AR00 message. This is necessary to be able...

This PR fixes the compile issue for newer version of jsoncpp available in the current version of Ubuntu 22.04.

## Motivation Currently we cannot use CUDNN based modules in loss modules as they are incompatible with vmap used in most of the losses. Particularly for RNN modules this leaves...

enhancement