The authors developed MFPG-PPO, a multi-fidelity variant of proximal policy optimization.
Multi-Fidelity Control Variates Stabilize Data-Scarce Reinforcement Learning
A new policy gradient algorithm uses cheap low-fidelity simulator data to reduce variance, enabling stable learning with as few as four real-robot episodes per update.
Top University
Xinjie Liu · Ruihan Zhao · Anirban Chaudhuri · Cyrus Neary · Ufuk Topcu · David Fridovich-Keil
University of Texas at Austin · University of British Columbia
Research Digest··3 min read
The authors introduce MFPG-PPO, an extension of the multi-fidelity policy gradient framework to actor-critic methods.
Why this paper
From University of British Columbia and University of Texas at Austin
In one line
Multi-fidelity policy gradients stabilize data-scarce on-policy RL by using biased low-fidelity data as a variance-reducing control variate.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§