-
Hello,
You advertise tianshou as being fast and provide in the readme a comparison table.
However, no reference code is linked to reproduce the results.
So, I decided to create a colab notebook…
-
I am a beginning learner in DRL. When I run this project on linux, there are many problems due to the incorrect version of the installation packages.I use python=3.6.13,Textworld=1.0.0,pytorch=0.4,te…
-
## Question
Why does the zoo call standard `make_vec_env()` for all environments, including Atari, when sb3 has a special function for it `make_atari_env()`?
## Train of thought
- train.py calls …
-
- creating docker image (for backup)
- creating singularity image
-
## Purpose
The purpose of this issue(discussion) is to introduce a series of pr in the near future targeted to releasing tianshou's benchmark for MuJoCo Gym task suite using onpolicy algorithms alrea…
-
感谢您的分享!因为你的网络更新和论文作者的不一样,我的疑问如下:
本repo中,`for _ in range(args.max_steps)` 这行代码是表示执行`max_step=1000`之后开始更新1000次吗?
```python
if j == args.max_steps - 1:
up_st = time.time()
…
-
I am using PASCAL_VOC Ddataset to do the training.
When I executed the command "python tools/train.py configs/pascal_voc/faster_rcnn_r50_fpn_1x_voc0712.py --gpus 1 --work_dir merge-output" to do the …
-
I am planning to experiment with population-based training and self-play, similar to the recent DeepMind's Q3 CTF paper. The obvious requirement would be the ability to train the agents to play agains…
-
Hello, good implementation of the DRL algos! I have been struggling quite a bit trying to understand how to incorporate an LSTM into the model and how to handle the hidden states and your repo seemed …
-
## Purpose
The purpose of this issue(discussion) is to introduce a series of pr in the near future targeted to releasing a benchmark(sac, td3, ddpg) on mujoco environments. Some features of tianshou …