Action Chunking Proximal Policy Optimization with Feedback Correction
cs.LG, cs.RO
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/hshhahn/ACPPO
Terminology
Sources
- Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
- VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning
- Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
- SEAR: Sample Efficient Action Chunking Reinforcement Learning
- OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation
- Proximal Policy Optimization Algorithms
- Chunk-Guided Q-Learning
- Residual Off-Policy RL for Finetuning Behavior Cloning Policies
- Real-Time Execution of Action Chunking Flow Policies
- Leave No Observation Behind: Real-time Correction for VLA Action Chunks
- Real-Time Robot Execution with Masked Action Chunking
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Training-Time Action Conditioning for Efficient Real-Time Chunking
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks