Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning
cs.LG, cs.AI, cs.RO
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/google-research/google-research
Project page: https://xinjie-liu.github.io/mfpg-ppo/ABSTRACT
Terminology
Sources
- PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
- Auto-Encoding Variational Bayes
- A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies
- Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
- A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators
- Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- RSL-RL: A Learning Library for Robotics Research
- Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization
- ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks