agents
agents copied to clipboard
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Hi, I am trying to train LinUCB or LinTS policy for my data. Policy is getting trained as well but it seems policy is selecting one particular arm for all...
I am trying to train LinUCB and LinTS with arm features. But it seems training time for these models are pretty high, with global features of ~200D and per arm...
Hi, Can we have some tutorials on Multi objective optimization and constraint optimization ?
Hi, I'm training with Q Networks. This is the first time I'll be using Q Networks so I am not sure why I am getting an error. Here's my code...
I think there's an error when using the tensor flow EnvironmentSteps metric. Let's say we're using parallel environment (with 10 envs) and setting collect_steps_per_iteration (to 5) in a DynamicStepDriver. I...
Hello, This is more a feature enhancement. For environments that are unstable i.e. that rarely return a mjWARN_BADQACC would be great if instead of abruptly stopping the training would return...
Dear authors: I want to save an object of DistributionNetwork, is there any solution? I could only think of `pickle` which directly save the object, but I didn't find any...
When passing a `TimeStep` or `Trajectory` to `tf.print`, the output presents the objects incorrectly in that some field values get printed in the wrong places. The following code demonstrates this:...
I am having an issue with the saved model trigger when using the learner API. Over a long enough time period, the saved model trigger has no limiter for the...
Use checkpointing from tf_agent, and report a lot of these warnings. Cannot disable these warnings.