Solving CartPole Without Gradients: Simulated Annealing
🔒
https://dev.to
«In the previous post, we solved CartPole using the Cross-Entropy Method: sample 200 candidate policies, keep the best 40, refit a Gaussian, repeat. It worked beautifully, reaching a perfect score of 500 in 50 iterations....»
Automatische Weiterleitung...
1.5s