-
I am looking for a simple library to implement parameter sharing in multi-agent RL using single-agent RL algorithms. I have just discovered Tianshou and it looks awesome, but I have a problem with the…
-
Hi
in the stable-baselines implementation, HER does not support prioritized replay buffer. In the HER Paper they state that: "Prioritized experience replay (....) is orthogonal to our work and bot…
-
Currently, the output format is line-based, but to parse it, you need to split it based on whitespace separators. This isn't a *huge* problem, but it's not the cleanest way to programmatically analyze…
-
This should make the code much more comprehensible, especially with the number of arguments we have. And at the same time resolve a lot of maintainability issues.
-
Hi
I just want to be sure that the TFUniform Replay buffer is priorities. My assumption is yes, but I can't really confirm it from the API docs.
Thanks in advance
-
Is there any plan to implement support for Prioritized Experience Replay, as described either in the original PER paper (https://arxiv.org/abs/1511.05952), or in the Ape-X one (https://openreview.net/…
-
From Piazza:
> I'm troubleshooting in the deep Q learning package and I'm having a problem with the DQExperience object. The object is defined in 'prioritized_experience_replay.jl' and is as follow…
-
**[OpenAI Baselines](https://github.com/openai/baselines)** is a set of high-quality implementations of reinforcement learning algorithms. These algorithms make it easier for the research community to…
-
I would be willing to work on this as my priority task this week if this idea is accepted.
When a CorsixTH player experiences a Lua error they may not find time to report it, so CorsixTH could ask th…
-
**Describe the bug**
As requested in the discord, for more readability, here is our feedback of DataStore:
Two months ago, we were advised to replace our whole backend architecture which was lying…