ml-agents icon indicating copy to clipboard operation
ml-agents copied to clipboard

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement lea...

Results 212 ml-agents issues
Sort by recently updated
recently updated
newest added

**Describe the bug** Learning crashes after around 3 seconds. The unity scene stops playing automatically, no errors in unity console. **To Reproduce** I don't know how to reproduce it, just...

bug
stale

### Proposed change(s) Crawler, Walker, and Worm all have TouchedTarget methods to add +1 reward that are, as near as I can tell, completely unused. These are not mentioned anywhere...

**Describe the bug** --num-envs doesn't work on ubuntu. Multiple instances of the game binary and mlagents-learn spawn but only one of them is used. Probably due to grpc and fork...

bug
stale

**Describe the bug** the new to unity ml agent,when i drag the release code into unity patform , and try to run the basic "3D ball" ,error happend **Console logs...

bug
stale

ML Agents 1.9 Training Area Replicator, to avoid having to explicitly create multiple Training Area(With its Child Agents and Enemies etc) as multiple Training Area Game Objects in my Scene....

discussion
stale

*Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: ``` $pip3 install mlagents==0.28.0 $mlagents-learn --help # or any other...

bug

I find this useful for controlling handles and other objects which could potentially be rapidly spinning. It allows the model to make better predictions of object location.

Classes in the `com.unity.ml-agents.extensions` package might get more use if people knew they existed. Add them to docs here.

**Is your feature request related to a problem? Please describe.** Submitting a request for a config file parameter where you can opt out of deterministic_discrete_actions branch in the neural network...

request

We currently have example projects for ML-Agents, settings that are explained, code examples on how to setup and run an environment. I am however missing one step, and that is...

request