Machine-Learning-6.867-homework

Machine-Learning-6.867-homework copied to clipboard

AI raycasting game to simulate self driving for saving people's lives https://fatalfeel.blogspot.com/2013/12/ppo-ai-on-raycast-3d-game-self-driving.html

fatalfeel

solution to required update.

2

alias ddConsoleApp=$HOME/path-to/build/bin/ddConsoleApp should be path to -> **director/build/install/bin/directorPython** all imports inside codes are need to be replaced from **ddapp** to **director**.

ikoc

References to ddConsoleApp are outdated

4

In the new version of `director`, it's now called `directorPython`. In addition, import statements referring to `ddapp` should be changed to `director`.

vtjeng

allow option for obstacles to be in inner 70% of world

1

manuelli

- [x] Implement abstract Q-Learning Class - [x] SARSA, Q-Learning, should all be subclasses Methods to implement - [x] SARSA, see #32 - [ ] policy search / policy gradient,...

manuelli

SARSA

1

- [x] Implement SARSA update - [x] Test it for convergence with a known policy, i.e. our simple controller - [x] Implement full SARSA policy updates

manuelli

Start thinking about policy gradient methods. What would we need to implement them? What should be the parametric form of the policy?

manuelli