Exploration into some new research surrounding value networks
-
Updated
Feb 4, 2026 - Python
Exploration into some new research surrounding value networks
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.
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.
Hybrid Reinforcement Learning and minimax agent for Tablut game. Combines PPO trained value networks with alpha beta search for competitive play.
Tic-Tac-Toe agent trained by Deep Reinforcement Learning
A Deep Reinforcement Learning technique incorporating Actor Critic framework and hybrid value networks to improve the dialogue policy.
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."