Oscar Ramirez

Thanks, for some reason in my case the cursor is at the start of the previous commands, not at the end.

Yeah, I actually just noticed this with V2 setups a day or two ago as well. It's an issue now that variables are not generated with unique names. They used...

You can look at the existing test case and add a new test in: https://github.com/tensorflow/agents/blob/master/tf_agents/environments/random_tf_environment_test.py#L93 You will probably have to add a new `__init__` param to the base `TFEnvironment` for...

That generalization should work. I think we just didn't have any envs that required it.

For an environment that has discrete actions you could do a similar pattern. In the case of continuous actions it gets a bit more tricky, you could use truncated normals...

YEs, the EOFError is caught and exceptions are logged. @LLouice do you have full logs? There should be a message with: ``` Error in enviroonment process: .... ``` `batched_py_environment.BatchedPyEnvironment(envs=[suite.load(...) for...

@ormandi thoughts on open sourcing `ReverbConcurrentAddBatchObserver`?

Yes, we should look into that. It's not clear to me if the update will help in this case. But it'll make the actors faster :)

See: https://github.com/tensorflow/agents/blob/master/tf_agents/environments/wrappers.py#L442