032b97912e
* working on ALE image pipelines that appear to lose data * transformation pipeline for ALE has been broken for a while and needed some cleanup to make sure that openCV tooling for scene transforms was actually working. * allowing history length to be set and passed through to history merge transforms Signed-off-by: Bam4d <chrisbam4d@gmail.com> * native image loader is not thread-safe so should not be static Signed-off-by: Bam4d <chrisbam4d@gmail.com> * make sure the transformer for encoding observations that are not pixels converts corectly Signed-off-by: Bam4d <chrisbam4d@gmail.com> * Test fixes for ALE pixel observation shape Signed-off-by: Bam4d <chrisbam4d@gmail.com> * Fix compilation errors Signed-off-by: Samuel Audet <samuel.audet@gmail.com> * fixing some post-merge issues, and comments from PR Signed-off-by: Bam4d <chrisbam4d@gmail.com> Co-authored-by: Samuel Audet <samuel.audet@gmail.com> |
||
---|---|---|
.. | ||
org/deeplearning4j/rl4j/mdp/vizdoom | ||
vizdoom |