Skip to main content
1 vote
0 answers
65 views

I am training a PPO agent using ML-Agents 4.0.2 on Unity 6.3 LTS and I am encountering a reproducible long-running stall that appears to be related to visual observations via RenderTexture. The setup ...
Ling's user avatar
  • 505
0 votes
0 answers
184 views

I followed all of the instructions in this video and installed al the the proper packages on top of Python 3.10.0 https://www.youtube.com/watch?v=v1d7SinTzEY&t=1s pip install torch torchaudio ...
Mich's user avatar
  • 3,724
0 votes
0 answers
71 views

I'm creating a Capture-the-Flag style game in Unity using ML-Agents. The setup includes: 2 Agents (one per team) Each team has a flag and a base NavMesh is also added to the floor. and navmesh agents ...
Avi Garg's user avatar
0 votes
1 answer
180 views

I have ml-agents up and running. When I run mlagents-learn from the command line, and play the game from the Unity Editor - everything works fine (the agent trains). But when I build the game and try ...
Rock Man's user avatar
1 vote
1 answer
163 views

I am trying to install mlagents. I got to the part in python but after creating a virtual enviorment with pyenv and setting the local version to 3.10, 3.9, and 3.8 it works on none of them. I upgraded ...
Joemama's user avatar
  • 15
0 votes
1 answer
93 views

I followed a tutorial on how to set up mlagents in unity and that all mostly went smoothly. I got a simple scene set up like this: With 3 Walls that reset the Episode and give a negative reward and ...
Abbadon's user avatar
  • 52
-3 votes
1 answer
66 views

I generated demo files (my play data) using the ml-agent package in Unity. How can I check how that file is structured? When I open the file with a text viewer, it is full of unintelligible text. I ...
Oksisiya's user avatar
0 votes
1 answer
61 views

Good morning. I am analyzing reinforcement learning results in TensorBoard. Is it appropriate to express the two metrics below with the following formula? Cumulative reward: the mean cumulative ...
Oksisiya's user avatar
0 votes
0 answers
104 views

I am looking for some insights on my rewards for seeker agent. I want him to be able to find hider in maze-like environment. I am using Raycasts (Ray Perception Sensor) as observation of environment. ...
Milos Stanojevic's user avatar
0 votes
0 answers
56 views

I'm training a rag doll to walk based on the WalkerAgent training from Unity and I changed a couple things around to better fit my purposes. Now every time any body part from the rag doll collides ...
Matt Clarke's user avatar
1 vote
0 answers
89 views

Edit to simplify the question: I can't figure out how to use transform.position = Vector3(x,y,z) while using an ArticulationBody. I have tried changing this.transform.GetComponent<ArticulationBody&...
The odor's user avatar
0 votes
1 answer
143 views

I already trained a .onnx model by ML-agents, but when I used barracuda to execute it, something went wrong. It said “KeyNotFoundException: The given key 'obs_0' was not present in the dictionary.” ...
flyingDumpling's user avatar
0 votes
1 answer
55 views

I'm trying to train the "Sorter" unity game using stable-baseline3 PPO algo. I used the following code but found that the observations received by the UnityToGymWrapper is different than ...
Maisa-ASM's user avatar
-1 votes
1 answer
81 views

I've been working with the ML-Agents library and trying to create a border around a randomly spawning target object. I created it, modified the script to teleport it to the same position as the target,...
Zelix75's user avatar
  • 81
-1 votes
1 answer
78 views

I am starting to discover ML-Agents in Unity, and have some working code with a cube moving in 2d. I have now implemented the detection of space key for the cube to jump. I would like to instruct ...
Laurent Crivello's user avatar

15 30 50 per page
1
2 3 4 5
8