-
CI test **linux://rllib:learning_tests_multi_agent_cartpole_crashing_appo_old_api_stack** is flaky. Recent failures:
- https://buildkite.com/ray-project/postmerge/builds/4702#018fdc87-d107-40c7-b2e8…
-
## Describe the bug
When training on `PettingZoo/MultiWalker-v9` with `Multi-Agent Soft Actor-Critic`, **all** losses (`loss_actor`, `loss_qvalue`, `loss_alpha`) explode after ~1M environment steps…
-
- d7926fad6e4c793566a4f8639c55112c8bebfdb9 FAILED [Buildkite :brain: rllib: learning tests tf2-static-graph](https://buildkite.com/ray-project/postmerge/builds/2063#018c588a-bb45-43c7-b895-dfbc1a15ee1…
-
When I run the example code, I met the error, the error logs is below:
(RolloutWorker pid=44372) ray::RolloutWorker.__init__() (pid=44372, ip=127.0.0.1, repr=)
(RolloutWorker pid=44372) File "py…
-
Hello,
I'm currently getting an SSL Certificate verfification error when trying to install the database.
Not quite sure whether it's from the request module from my end or from your server's side.…
-
### What happened + What you expected to happen
Something's broken with the SimpleQ TF2 action distribution, but I can't track down the bug. This doesn't happen with TF1/Torch.
### Versions / De…
-
ElegantRL and RLlib Training:
ValueError Traceback (most recent call last)
Cell In [28], line 4
1 #demo for rllib
2 ray.shutdown() #always shutdown pre…
-
### What happened + What you expected to happen
Initializing `ImpalaTF2Policy` currently throws a ValueError since `self.cur_lr` is a tf.Variable but the optimizer class only takes floats, LearningRa…
-
hello, I find you have use the marwil by rllib. And, I just test its examples by rllib cartpole .But, it generate NAN reward. Do you find it during using the rllib.
-
Hi,
Currently the only way I know how to change a legend is to click the edit button on an individual plot and then enter a custom legend such as:
```
[[ ${x}: ${y} ]] train:${config:epoch_loo…