-
now, I want to implement a reinforcement learing method--DDPG. It has eval network and target network, their have the same structure. but eval network through gradient update, target network need upda…
-
Nice work!
I read your article and wonder why you decide to use discrete action space?
Have you tried continuous action space?
Thanks!
-
你好 我看到在代码中，sac的actor也有target_net。这个在其他implementation，比如stable_baseline3, spinning_up都没有出现。 [Spinning Up: SAC](https://spinningup.openai.com/en/latest/algorithms/sac.html)中也有强调，
> Unlike in TD3, the n…
-
https://github.com/DLR-RM/stable-baselines3/blob/c895c1d46f5d24cc49ccb20e99089a141fe7f4c1/stable_baselines3/sac/sac.py#L215
Ref:
https://github.com/rail-berkeley/softlearning/blob/master/softlearn…
-
TorchBench CI has detected a performance signal.
Base PyTorch version: 1.11.0.dev20211103+cu102
Base PyTorch commit: 54241a9cfa1d4c5ee2096cd9acec1ae7bf623c37
Affected PyTorch version: 1.11.0.dev20…
-
https://github.com/Beep6581/RawTherapee/issues?utf8=%E2%9C%93&q=is%3Aissue+milestone%3Av5.9
-
```
eip: EIP-1329
title: Inalienable Reputation Token
author: Maxim Orlovsky , Andrey Sobol
discussions-to: this issue
status: WIP
type: Standards Track
category: ERC
created: 2018-08-13
```…
-
In "Demo_MultiCrypto_Trading" notebook I try to change the interval of data eg:
TRAIN_START_DATE = '2020-08-01' -- original START DATE=2021-09-01
TRAIN_END_DATE = '2021-09-20'
TEST_START_DATE …
-
Implement a baseline for SAC.
-
## 🐛 Bug
On 20210712, TorchBench Performance Score drops 0.8%. The reason are the following tests:
```
+-----------------------------------------+----------------+----------------+----------+
…