-
**Describe the bug**
For me all environment-parameters (as configured in the config.yaml file) show up as 0s in tensorboard at all timesteps.
**To Reproduce**
Run Training on the WallJump-scene…
-
What I did:
> Upgraded from tensorflow 2.2.0 to tensorflow 2.3.0
Implementation:
> from tf_agents.agents.dqn import dqn_agent
Error:
> File "C:\Users\ryans\source\repos\venvs\Python37…
-
I was following the example script for a custom loss function. I am interested in bootstrapping my policy with a dataset from an algorithmic supervisor. However, the demonstrations are not perfect so …
-
This applies to `resubmit` and probably to `clone` (Did not try).
Metadata fields are not copied to the recirculated packet unless you copy the entire metadata struct or you create a tuple of indiv…
-
**Describe the bug**
NullReferenceException: Object reference not set to an instance of an object
MLAgents.Batcher.SendAcademyParameters (MLAgents.CommunicatorObjects.UnityRLInitializationOutput aca…
-
## ℹ Computer information
- PowerToys version: 0.31.1
- PowerToy Utility:
- Running PowerToys as Admin: No
- Windows build number: 19042.789
## 📝 Provide detailed reproduction steps (if any)
…
-
Transfer LQR controller to PPO
variants:
1. make PPO policy a linear model and directly copy LQR law into the policy
1. make behavioural cloning of the LQR into a "standard NN"
-
Agent finished a curriculum, after the model had been saved the terminal showed 'IndexError: list index out of range'
```
2020-07-25 20:52:17 INFO [stats.py:129] Hyperparameters for behavior nam…
-
**Describe the bug**
I am using mlagents 0.18.0. While I setup everything and started training with provided example environments, it keeps giving me KeyError from trainer and AttributeError from ten…
-
Hello, i noticed that there is far less documentation for BC than for PPO. Of course I have read this document /docs/Training-Imitation-Learning.md and there is instructuin how to use BC but almost no…