Skip to content

Actions: wadekarg/RL-interactive-lab

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
23 workflow runs
23 workflow runs

Filter by Workflow

⌥ + click/return to exclude

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Add Python code tab to GridWorld lab Deploy to GitHub Pages #23: Commit cd66c70 pushed by wadekarg
36s master
master
36s
Add standalone Python files and update README with Python tab feature Deploy to GitHub Pages #22: Commit 37281f4 pushed by wadekarg
43s master
master
43s
Fix missing PythonCodeEntry type import Deploy to GitHub Pages #21: Commit aebe9a6 pushed by wadekarg
40s master
master
40s
Add CodeMirror editor, Pyodide runtime, download button, rich comments Deploy to GitHub Pages #20: Commit b4f0f47 pushed by wadekarg
22s master
master
22s
Unhide CartPole and Rocket Landing tabs Deploy to GitHub Pages #19: Commit 875c72e pushed by wadekarg
49s master
master
49s
Hide CartPole and Rocket Landing from the live app Deploy to GitHub Pages #18: Commit 1f2f3ce pushed by wadekarg
31s master
master
31s
Clarify Q-Learning param labels and descriptions to match optimal def… Deploy to GitHub Pages #17: Commit c5b883b pushed by wadekarg
38s master
master
38s
Increase default maxSteps 100k→500k for reliable Q-Learning convergence Deploy to GitHub Pages #16: Commit 9b836bc pushed by wadekarg
39s master
master
39s
Fix Q-Learning catastrophic forgetting: alphaMin 0.1→0.001, epsilonMi… Deploy to GitHub Pages #15: Commit 747e17f pushed by wadekarg
37s master
master
37s
Fix convergence bugs in REINFORCE and Q-Learning Deploy to GitHub Pages #14: Commit b48fb19 pushed by wadekarg
37s master
master
37s
Improve episode chart: tooltip shows Episode N, add Steps y-axis label Deploy to GitHub Pages #13: Commit 7559f23 pushed by wadekarg
36s master
master
36s
Show raw episode steps in chart instead of rolling average Deploy to GitHub Pages #12: Commit cfac845 pushed by wadekarg
32s master
master
32s
Remove neural network algorithms, keep classic RL only Deploy to GitHub Pages #11: Commit b3b9c2f pushed by wadekarg
35s master
master
35s
Remove code duplication across neural RL agents and UI Deploy to GitHub Pages #10: Commit e1d1d86 pushed by wadekarg
22s master
master
22s
Add DQN, Neural REINFORCE, and A2C algorithms to CartPole RL lab Deploy to GitHub Pages #9: Commit 992c941 pushed by wadekarg
37s master
master
37s
Tune CartPole hyperparameter defaults based on benchmark results Deploy to GitHub Pages #8: Commit 178b967 pushed by wadekarg
35s master
master
35s
Improve tablet (iPad) responsiveness across the app Deploy to GitHub Pages #7: Commit 3b75c50 pushed by wadekarg
39s master
master
39s
Display Navigate MDP states as 2x2 grid instead of vertical stack Deploy to GitHub Pages #6: Commit 5984e76 pushed by wadekarg
41s master
master
41s
Remove unused colors array from StochasticPolicyWidget Deploy to GitHub Pages #5: Commit 354cc16 pushed by wadekarg
35s master
master
35s
Fix stochastic policy widget: use static Tailwind classes for action … Deploy to GitHub Pages #4: Commit cce132d pushed by wadekarg
24s master
master
24s
Fix mobile responsiveness: hamburger nav, overflow, canvas scaling Deploy to GitHub Pages #3: Commit ae4f86e pushed by wadekarg
35s master
master
35s
Fix vite base path: hardcode /RL-interactive-lab/ to avoid process.en… Deploy to GitHub Pages #2: Commit c7bc4b8 pushed by wadekarg
34s master
master
34s
Add GitHub Actions workflow for GitHub Pages deployment Deploy to GitHub Pages #1: Commit 6da24b2 pushed by wadekarg
24s master
master
24s