Show HN: I built an autopilot for the lunar lander game

Post by paradite » Fri, Mar 10, 2023, 1:26 PM UTC

hcrisp wrote: post #37

paradite wrote: post #34

Lunar lander is a one of the problems in Open AI Gym, where you test AI against standard set of problems: https://www.gymlibrary.dev/environments/box2d/lunar_lander/ Then you have stable baselines which implements popular reinforcement learning algorithms to solve these gym problems: https://stable-baselines3.readthedocs.io/en/master/ Shamless plug: I've built a series of games where you solve puzzles (2048) / toy pr…

Yes, I would like to see the environment ported to Python, wrapped in gym, and given a good shaped reward, i.e. like reward = prior_height_delta - (height - target_height) - fuel_cost. Run Stable Baselines PPO or DQN on that and it should converge to something close to an optimized MPC controller.

Post by zengargoyle » Fri, Mar 10, 2023, 2:00 PM UTC

simonh wrote: post #23

That's cool, but it has a very conservative descent profile and would use a ton of fuel. Having played Kerbal I'm used to attempting fuel efficient landings, which means more of a suicide burn approach, but of course this game doesn't keep track of that. There's something timelessly appealing about lunar lander games. The very first game I ever played on a computer, written in BASIC, was a 'turn based' one dimensiona…

Post by Aperocky » Fri, Mar 10, 2023, 2:07 PM UTC

Post by szhu » Fri, Mar 10, 2023, 2:38 PM UTC

ricardobeat wrote: post #15

timmaxw wrote: post #8

I wanted to go for a record of as many flips as possible. So I boosted up to 25,000 feet; started spinning until it was doing about one flip per second; waited a few minutes; then turned on the autopilot to come into a landing. The autopilot did a perfect job of stopping the rotation and lateral motion, so the lander came down straight as an arrow. Unfortunately, the autopilot didn't even try to decelerate! I crashed…

The target velocity is a factor of height, and the autopilot has “160” hardcoded as the ceiling, so going above that means it will never decelerate fast enough. https://github.com/szhu/lunar-lander-autopilot/blob/master/a...

Post by jkonline » Fri, Mar 10, 2023, 3:10 PM UTC