-
I'm proposing holding space for a study group on the dl course by hugging face (https://huggingface.co/deep-rl-course/unit1/introduction?fw=pt)
I need to have it discussed in a c-base circle
the circl…
-
-
##### Expected behaviour:
Environment fully supports TF2
##### Actual behaviour:
Only 1.5 is supported for certain scripts
I ran the [automatic upgrade](https://www.tensorflow.org/guide/upgra…
-
Issue #817 was closed with this response:
> We fell a little behind. The Python bindings are done in SWIG. I think that can be quickly repurposed into .Net bindings, once done. So it shouldn't be too…
-
### ❓ Question
Hi all!
I hope to integrate RNN(LSTM/GRU) to off-policy algorithm(SAC and TD3) without multiprocessing like A3C.So I checked SB3-contrib code about recurrentPPO and [the recurrent…
-
-
微博内容精选
-
## Problem Description
[Muesli](https://arxiv.org/abs/2104.06159) is a next-generation policy gradient algorithm from DeepMind that performs exceptionally well. Notably, it can match MuZero’s SOTA …
-
### What is the problem?
It seems that the states being passed to TorchModelV2 and TFModelV2 are incorrect, as the shapes don't seem to match up. Please see the stack traces below. Note that I am u…
-
_From @Ailanz on March 6, 2018 15:50_
Hi, I have a question. I want to train DDQN / A3C with comp graph that has multiple inputs. Half of the input will feed into LSTM while the other half feed into …