Fetching the paper…

Reading the bibliography…

2017

Learning to Run with Actor-Critic Ensemble

Huang, Zhewei, Zhou, Shuchang, Zhuang, BoEr et al.

Original
PDF
Post on X

Understand

We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm.

At inference time, our method uses a critic ensemble to select the best action from proposals of multiple actors running in parallel.
By having a larger candidate set, our method can avoid actions that have fatal consequences, while staying deterministic.
Using ACE, we have won the 2nd place in NIPS'17 Learning to Run competition, under the name of "Megvii-hzwer".

Learning to Run with Actor-Critic Ensemble · Around

Built on

Ensemble methods in machine learning
Thomas G Dietterich et al · 2000
Earlier work this paper cites.
Continuous control with deep reinforcement learning
Original
Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra · 2015
Earlier work this paper cites.

Similar

Self-normalizing neural networks
Original
Günter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter · 2017
Cited alongside, same era.
Run, skeleton, run: skeletal model in a physics-based simulation
Original
Mikhail Pavlov and Sergey Kolesnikov and Sergey M. Plis · 2017
Cited alongside, same era.

Then

Distributional policy gradients
Anonymous · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…