PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning
cs.RO
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
- Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
- OpenVLA: An Open-Source Vision-Language-Action Model
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- RFTF: Reinforcement Fine-tuning for Embodied Agents with Temporal Feedback
- Interactive Post-Training for Vision-Language-Action Models
- BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents
- Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
- World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
- Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents
- RISE: Self-Improving Robot Policy with Compositional World Model
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
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
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving