-
Hello, where is the code for the prioritized experience replay? I only saw the original experience replay algorithm.
-
The prioritized replay buffer is sampling just a set of experiences with very high probability over and over, in a window of samples. So far, the bellman errors seem ok, the modified agent pipeline al…
-
Dear maintainers, I'm reading here:
https://github.com/LibreSignal/LibreSignal/issues/28#issuecomment-207661671
that the people behind f-droid are willing to have LibreSignal distributed there.
What…
-
-
See bounty link here -
https://www.bountysource.com/issues/48048939-dynamic-recompiler
Conditions:
* A dynarec system for Beetle PSX, preferably written in C or else C++98. Portability to the v…
-
As of 5c252ea, this repo has been checked over several times for discrepancies, but is still unable to replicate DeepMind's results. This issue is to discuss any further points that may need fixing.
…
-
I need to test ppo2 with a prioritized experience replay and I wonder if anyone wrote a similar integration before I go ahead and write it from scratch.
-
thank you for sharing your project. I've been testing several projects that use PPO as well as doing mine and so far could not get results, however when training yours I see steadily increasing reward…
ghost updated
5 years ago
-
Your PER implementation is rank-based and the default hyperparameter values (alpha=0.6, beta=0.4) that you have written down are actually the "ideal" combination for proportional PER and not rank-base…
-