arXiv AI
Does "Do Differentiable Simulators Give Better Policy Gradients?" Give Better Policy Gradients?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 5
Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning
The paper introduces Multi‑Fidelity Policy Gradient (MFPG) methods that combine scarce, high‑fidelity (HF) reinforcement‑learning data with abundant, low‑fidelity (LF) data to stabilize training. Unlike prior approaches that directly optimize biased LF objectives, MFPG uses LF data only to construct a control variate that reduces variance without biasing the policy gradient. The authors extend MFPG to modern actor‑critic algorithms, notably a budget‑aware MFPG‑PPO that preserves cross‑fidelity correlation, monitors estimator uncertainty, and allocates a fixed sampling budget between HF and LF sources. Experiments on simulated robot locomotion and a physical Franka arm show that MFPG‑PPO consistently outperforms standard PPO trained on HF data alone and matches performance achieved with 16× more HF data on the hardest tasks, while enabling stable learning with as few as four real‑robot episodes per update.
arXiv Machine Learning
Jun 11
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv Machine Learning
Jul 30
Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning
arXiv:2607. 26509v1 Announce Type: new Abstract: Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement.
arXiv Machine Learning
3d ago
Best Policy Tracking in Reinforcement Learning
The paper investigates how non‑monotonic performance dynamics in single‑task reinforcement learning affect policy selection. By introducing post‑hoc diagnostic metrics, the authors evaluate common selection strategies on continuous‑control benchmarks and find that typical practices often miss the best policy, leading to suboptimal performance and wasted computation. They propose a validation‑based selection method that better approximates the best visited policy while improving efficiency.
arXiv AI
Jun 6
Retry Policy Gradients in Continuous Action Spaces
arXiv:2606. 05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses.
arXiv AI
Jun 10
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
arXiv:2606. 11087v1 Announce Type: cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.