# Learning to Run with Actor-Critic Ensemble

arXiv: https://arxiv.org/abs/1712.08987 · HTML: https://mlsanity.com/paper/1712.08987/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Dec 2017.

## Built on by (most cited first, 8 of 8)

- [MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation](https://mlsanity.com/paper/2309.14236/) (2023)
- [Continuous Control With Ensemble Deep Deterministic Policy Gradients](https://mlsanity.com/paper/2111.15382/) (2021)
- [Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control](https://mlsanity.com/paper/2207.13730/) (2022)
- [Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions](https://mlsanity.com/paper/2410.11833/) (2024)
- [Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training](https://mlsanity.com/paper/2209.14488/) (2022)
- [TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control](https://mlsanity.com/paper/2204.10685/) (2022)
- [Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning](https://mlsanity.com/paper/2209.15078/) (2022)
- [A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic](https://mlsanity.com/paper/2603.28971/) (2026)

## Abstract (arXiv)

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".