-
你好，最近刚接触到snn，你们的仿真平台做的非常好! 不过我之前没有用源码装过库，不太会。。。安装gpu版时一直报错，网上搜了是pytorch和cudatoolkit版本不匹配问题，可是我是在官网下的版本匹配应该没问题，也设置了CUDA_HOME的环境变量，希望得到帮助，万分感谢！
我的版本：python3.7，pytorch1.8.1，cuda10.2，cudnn7
-
- `AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'`
- `TypeError: len is not well defined for symbolic Tensors. (activation_4/activation_4/Identity:0) Please call `x.shap…
-
Hi
1. Can Catalyst implementations be used in multi-agent environments?
2. Does Catalyst support vectorized environments?
I am more specifically talking about DQN/Rainbow (and not interested in…
rfali updated
3 years ago
-
### What is the problem?
This is a regression bug. After updating from ray 1.2.0 to later versions, SAC (with torch framework, torch version 1.8.1) stopped converging at all on my environment. See …
-
## 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 …
-
Hi,
I'm interested to use your ego attention method in your paper with highway env. But I don't know about rl-agent and want to use it in my own PyTorch implementation.
As I understood from your …
-
I want to control the learning rate for the DQN algorithm, and implement something like torch.optim.lr_scheduler.ReduceLROnPlateau (but slightly more complex). I implemented a mixin for my policy and …
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
-
Why is there no frame stacking [in the Atari wrapper](https://github.com/DLR-RM/stable-baselines3/blob/master/stable_baselines3/common/atari_wrappers.py#L207) but **only max-pooling** over the last 2 …
-
This code https://github.com/datamllab/rlcard/blob/c6673c3b9bfc41461423d355febe4fded45fbede/rlcard/agents/dqn_agent_pytorch.py#L34 tried to import `Memory` from `dqn_gent` which is implemented with te…