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
A Deep Reinforcement Learning technique incorporating Actor Critic framework and hybrid value networks to improve the dialogue policy.
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."