muzero-general

muzero-general copied to clipboard

### Search before asking - [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar bug report. ### 🐛 Describe the bug Tried this out on a remote server...

jrjbertram

Improving Atari hyperparameters

4

After training according to the configuration file of Breakout, the effect cannot reach 800+ as stated in the paper. Can anyone give us a result about Atari game, detailed configuration...

xiaolonghao

RuntimeError: module must have its parameters and buffers on device cuda:0 (device_ids[0]) but found one of them on device: cpu

3

Any idea how to fix this error below? This happens for every sample game. ray==1.5.0 torch==1.9.1+cu111 Thanks ``` 2021-09-24 17:22:36,982 ERROR worker.py:79 -- Unhandled error (suppress with RAY_IGNORE_UNHANDLED_ERRORS=1): ray::Reanalyse.reanalyse() (pid=11872,...

lukaszkn

Training step always 0

2

hi, i am trying to train the network, but the training step always remain as zero. is this expected behaviour?

yeekit24

raw install has ray problem

1

### Search before asking - [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar bug report. ### 🐛 Describe the bug I created new venv, then installed per...

EngrStudent

### Search before asking - [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar bug report. ### 🐛 Describe the bug In **Learning and Planning in Complex Action...

ManorZ

### Search before asking - [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar feature requests. ### Description Is it possible to adapt the open-source implementations to accelerate...

szrlee

Render model

1

### Search before asking - [X] I have searched the MuZero [issues](https://github.com/werner-duvaud/muzero-general/issues) and found no similar bug report. ### 🐛 Describe the bug I was trying to render my model...

theeduardomora

Hi all, I have been played around several games implemented here, training Connect4 in particular for the last 36 hours. I'm looking to improve some of the implementations, however, I'm...

onegigbyte

RAM memory usage of SelfPlay.continuous_self_play() keeps growing

8

I'm using ubuntu 18.04 and ray 1.3 Even when capping replay_buffer_size the memory increases almost linearly for each SelfPlay.continuous_self_play() agent. Is this a known bug? Are there any suggestions to...

adalsteinnpals