MBRL-DeepMPC
PublicEfficient 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.
cross-entropy-methoddeep-learningdeep-neural-networksdeep-reinforcement-learninggym-environmentmodel-based-reinforcement-learningmodel-predictive-controlmujoco-environmentspythonreinforcement-learning
Creat：2024-12-02T11:21:09
Update：2025-10-01T08:46:22
10
Stars
0
Stars Increase