To help the algorithm converge faster, I also pushed knowledge of falling to earlier states by heavily penalizing unstable configurations (e.g. To avoid this local optimum, I not only rewarded forward motion, but also gave a small amount of points for simply moving the ragdoll's legs back and forth. Unfortunately, this didn't work as well as I had planned - my first attempt ended up converging on a (rather entertaining) local optimum, and was unable to actually learn to take steps. I rewarded forward motion, penalized falling over, and ran the learner for around 8 hours at 10 states per second. Using various metrics to describe the state of the ragdoll, I set out to learn the optimal action given every possible state. Originally, I implemented the naive version of Q-learning I learned in my AI class. Start AI Stop AI Reset Ragdoll Use Neural Network Use Q-Table
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |