JackM323/JackBot
1
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects 2 Releases Wiki Activity

direct and residual movement inconsistency fixed

Browse Source
This commit is contained in:
JackM323
2026-08-27 21:40:57 +02:00
parent cd870a4afc
commit 4cc2d37d94
8 changed files with 109 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -13
View File
@@ -144,17 +144,7 @@ The machine learning system trains the hexapod to move using a combination of Be
### ML Workflow Steps
The policy input contains:
* 18 joint angles from the robot, and
* 4 command dimensions describing the desired motion direction and yaw rate.
The policy output is:
* 18 continuous values, one per joint, describing how much each joint should change.
This means the learning method is not controlling a discrete gait state directly. Instead, it learns a continuous control policy for the whole body.
The machine learning system trains the hexapod to move using a combination of Behavioral Cloning (BC) (optional) and Proximal Policy Optimization (PPO) driven by a multi-phase curriculum.
#### Methods implemented
The current ML stack uses:
@@ -307,5 +297,4 @@ In multi-robot vectorized training (`JackBotEnv`), individual robot failures are
When training with `--gui`, `JackBotEnv` includes dynamic visual feedback mechanisms:
* **Metrics HUD:** A live on-screen text overlay tracking active episode count, total step rate (FPS), average base height, roll/pitch angles, and cumulative per-robot rewards.
* **Leader Crown ($\text{👑}$):** A floating crown debug indicator tracks and positions itself directly above the base of whichever robot is achieving the highest cumulative reward in the multi-robot grid.
* **Metrics HUD:** A live on-screen text overlay tracking active episode count, total step rate (FPS), average base height, roll/pitch angles, and cumulative per-robot rewards.