Closed abdel closed 5 years ago
I agree with @abdel, it seems that Dopamine and TF-Agent strongly overlap. Although dopamine aims at being used for fast prototyping and benchmarking as the reproducibility has been put at the core of the project, whereas TF-Agent would be more used for production-level reinforcement learning algorithms. I would love seeing the two frameworks merging or at least having strong compatibilities to facilitate the move from prototyping to production-level code.
@psc-g fyi; we could have a discussion about this as a long term goal.
yeah, i think this would be a great thing to have. i imagine the use-case would almost exclusively be dopamine -> tf-agents, so we could focus on that without necessarily worrying about supporting the tf-agents -> dopamine direction.
On Mon, Mar 11, 2019 at 12:15 AM ebrevdo notifications@github.com wrote:
@psc-g https://github.com/psc-g fyi; we could have a discussion about this as a long term goal.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/tensorflow/agents/issues/15#issuecomment-471406981, or mute the thread https://github.com/notifications/unsubscribe-auth/ATYhMStE8lz7lc1j2rfiQUOqMekdUc75ks5vVeZYgaJpZM4bkN8c .
Closing this issue, please reopen if we need to track this actively or if you have further questions.
There seems to be a lot of overlap between objectives of TF Agents and the Dopamine framework, are there any plans to share or combine these frameworks, or are they intentionally made separate?