Jerome Lenssen

How to customize Actor policy in Actor-Learner setup

1

Hi, I am following https://github.com/tensorflow/agents/tree/master/tf_agents/experimental/distributed/examples/sac to implement an Actor-Learner environment for DDQN (similar to [Ape-X](https://arxiv.org/abs/1803.00933), page 6). How can I adapt the actor-policies that get their policy variables from the...

Feature request: Support subdirectories in file attachments of experiments

1

Hi, For larger experiments that generate a lot of data, it would be useful to group related files (e.g. plots) in subdirectories for easier browsing of the data. Currently, I...