First Order Model-Based RL through Decoupled Backpropagation
cs.RO, cs.AI, cs.LG
Submitted: 2025-08-29
Updated: 2025-09-04
Project page: https://machines-in-motion.github.io/DMO
Terminology
Sources
- Extreme Parkour with Legged Robots
- Robot Parkour Learning
- CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning
- Humanoid Parkour Learning
- Soft Actor-Critic Algorithms and Applications
- Proximal Policy Optimization Algorithms
- Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation
- Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- Model-Augmented Actor-Critic: Backpropagating through Paths
- Model-Ensemble Trust-Region Policy Optimization
- Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
- MOPO: Model-based Offline Policy Optimization
- Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
- Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
- PWM: Policy Learning with Multi-Task World Models
- Investigating Compounding Prediction Errors in Learned Dynamics Models
- UniZero: Generalized and Efficient Planning with Scalable Latent World Models
- ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies