-
How do you plan to incorporate SPI into your method? Have you considered using Reverb with Deepmind?
Did you see the efficiency in the results compared to agent57?
-
**Describe the bug**
The following python code, modified from example/sample_atari.py to use r2d2 with sequence_length=80, gradually consumes lots of memory until the whole process is killed. Altho…
-
Hi, @michaelnny ,
Thanks for your repository, helped me a lot. I encountered an issue while using it and would like to seek your advice.
When using the R2D2 method, data generated by the intera…
-
I know that you mentioned on your blog that you are limited by your compute power; I guess I am just asking if you replicated any results from the Agent57 paper, especially when it comes to hard explo…
-
I am not sure how you got this from Agent57, (agent.py). I don't see this mentioned in the original paper.
line 676 "priorities = 0.8 * ext_priorities + 0.2 * int_priorities"
Thanks
-
I'm currently reimplementing Agent57 to understand the concepts thoroughly, im almost done except batch inference and multi actor, retrace, meta controller, bandits, and multi head q value. Would you …
-
c_t = torch.minimum(torch.tensor(1.0), pi_a_t / (mu_t + eps)) * lambda_
mu_t should be mu_a_t right? Is this a bug or intentional?
-
I love your work, are we going to see an implementation of MEME ( https://arxiv.org/abs/2209.07550 ) by paper anytime in the future? I think it's a big improvement upon Agent57.
Thank you
-
I'm having issues running multigpu on Agent57 in the same way I run them on let's say R2D2.
Where I change
` actor_devices = [runtime_device] * FLAGS.num_actors`
to
` actor_devices = [torch…
-
I'm sort of a newbie, how can I replace the atari env so that it supports retro env?