GoMoKu combine with Monte Carlo Search Tree and value network
-
Updated
Sep 29, 2018 - Python
GoMoKu combine with Monte Carlo Search Tree and value network
Kispagi (which means to pay with kisses in Esperanto) is an app that connects to your favourite(s) issue tracker(s) or project manager(s) (gitlab, github, redmine, etc) to read the contributed hours and calculate a payment distribution with different rules.
A Deep Reinforcement Learning technique incorporating Actor Critic framework and hybrid value networks to improve the dialogue policy.
Efficient Model-Based Deep Reinforcement Learning with Predictive Control: Developed a Model-Based RL algorithm using MPC, achieving convergence in 200 episodes (best case) and 1000 episodes on average, outperforming SAC/DQN (10,000+ episodes). Enhanced sample efficiency by 80-90% using learned dynamics and CEM for trajectory optimization.
Tic-Tac-Toe agent trained by Deep Reinforcement Learning
Add a description, image, and links to the value-network topic page so that developers can more easily learn about it.
To associate your repository with the value-network topic, visit your repo's landing page and select "manage topics."