Learning to Run with Actor-Critic Ensemble
Not on the map. Why?
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".
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Dec 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 4; 2023: 1; 2024: 1; 2025: 0; 2026: 1.
8 papers.
- 2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulationcited by 27
- 2021Continuous Control With Ensemble Deep Deterministic Policy Gradientscited by 8
- 2022Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Controlcited by 3
- 2024Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functionscited by 3
- 2022Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Trainingcited by 1
- 2022TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process controlcited by 0
- 2022Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learningcited by 0
- 2026A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Criticcited by 0
- 2026A Pontryagin Method of Model-based Reinforcement Learning via Hamiltonian Actor-Critic30 Mar 2026
- 2024Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions15 Oct 2024
- 2023MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation25 Sep 2023
- 2022Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning29 Sep 2022
- 2022Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training29 Sep 2022
- 2022Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control27 Jul 2022
- 2022TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control22 Apr 2022
- 2021Continuous Control With Ensemble Deep Deterministic Policy Gradients30 Nov 2021