Human Control
Drive the arm with continuous shoulder, elbow, and grip control
Create a session to begin.
Continuous Control Recovery Track
Grabber is the live continuous-control lane for DRL: human play, PPO checkpoint playback, and a structured training workflow with learning-timeline snapshots. It keeps the Reacher lineage visible without depending on the legacy Unity runtime.
Human Control
Create a session to begin.
Play
Keyboard: `A/D` shoulder, `J/L` elbow, `W/S` grip close/open. Hold the keys to keep stepping.
Shoulder
Elbow
Grip
Machine Play
Train or load a checkpoint to inspect it here.
Training
Environment
Reward
PPO
Learning Timeline
Choose a completed training job to inspect its timeline snapshots.
Jobs
No job selected.
Curator Guide
The old Reacher branch is rich but too entangled with Unity, ML-Agents, and older environment assumptions to become the first live continuous-control experience. Grabber preserves the core teaching shape instead: continuous actions, a visible arm, a clear target, and a staged objective that lets users watch learning improve over time.
Live first
Grabber keeps the arm-control intuition of Reacher but replaces the legacy simulator with a browser-native 2D task. That removes the old runtime baggage while keeping the ideas users actually need to see: continuous control, grasp timing, and return-home behavior.
Task structure
The policy does not only need to reach. It must approach the coin, close the grip inside the capture radius, keep possession, and then bring the coin back into the visible home zone for a short dwell window.
How to read the page
Human play, machine playback, and training all share the same three control axes: shoulder, elbow, and grip. The color-coded gauges make it obvious which degree of freedom is doing the work on each step.
Why PPO leads
The historical Reacher archive is DDPG-heavy, but Grabber uses PPO for the live page because it is a cleaner fit for the bounded worker pipeline and a more stable first public training surface. The archive still points back to DDPG as lineage, not as the first runtime dependency.
Source Trail
The original project branch with Reacher notebooks, reports, environment notes, and auxiliary experiments.
source-material/classwork/project-reports/p2_continuous-control
Defines the original double-jointed target-reaching task, its observation space, and the continuous action framing.
source-material/classwork/project-reports/p2_continuous-control/README.md
The simpler historical Reacher lane that informs the live lab’s control vocabulary even though the runtime is different.
source-material/classwork/project-reports/p2_continuous-control/ddpg_single_agent
Actor-critic experiments, reward notes, and action-space references that sit behind the live Grabber page as archive lineage.
source-material/ddpg/reacher