Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning

2021-07-20 · ICLR 2022 4 · Denis Yarats, Rob Fergus, Alessandro Lazaric, Lerrel Pinto

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements that yield state-of-the-art results on the DeepMind Control Suite. Notably, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL. DrQ-v2 is conceptually simple, easy to implement, and provides significantly better computational footprint compared to prior work, with the majority of tasks taking just 8 hours to train on a single GPU. Finally, we publicly release DrQ-v2's implementation to provide RL practitioners with a strong and computationally efficient baseline.

📄 PDF Abstract BibTeX arXiv:2107.09645

Code (8)

facebookresearch/drqv2 공식 구현 pytorch

Asap7772/understanding-rlhf pytorch

architsharma97/medal pytorch

denisyarats/drq pytorch

mazpie/mastering-urlb pytorch

tajwarfahim/proactive_interventions pytorch

zhaoyi11/tcrl pytorch

zhou-henry/distributed-distributional-drq pytorch

Tasks

continuous-control Continuous Control Data AugmentationGPUreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Unsupervised Reinforcement Learning

EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

2024-03-01 · Shengjie Wang, Shaohuai Liu, Weirui Ye, Jiacheng You 외

Sample efficiency remains a crucial challenge in applying Reinforcement Learning (RL) to real-world tasks. While recent algorithms have made significant strides in improving sample efficiency, none have achieved consiste…

continuous-control Continuous Control Reinforcement Learning (RL)

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

2023-10-30 · Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang 외

Visual reinforcement learning (RL) has shown promise in continuous control tasks. Despite its progress, current algorithms are still unsatisfactory in virtually every aspect of the performance such as sample efficiency, …

continuous-control Continuous Control reinforcement-learning Reinforcement Learning+1

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

2022-09-24 · Sai Rajeswar, Pietro Mazzaglia, Tim Verbelen, Alexandre Piché 외

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Unsupervised Reinforcement Learning

Mastering Rate based Curriculum Learning

2020-08-14 · Lucas Willems, Salem Lahlou, Yoshua Bengio

Recent automatic curriculum learning algorithms, and in particular Teacher-Student algorithms, rely on the notion of learning progress, making the assumption that the good next tasks are the ones on which the learner is …

Policy Gradient Methods in the Presence of Symmetries and State Abstractions

2023-05-09 · Prakash Panangaden, Sahand Rezaei-Shoshtari, Rosie Zhao, David Meger 외

Reinforcement learning (RL) on high-dimensional and complex problems relies on abstraction for improved efficiency and generalization. In this paper, we study abstraction in the continuous-control setting, and extend the…

continuous-control Continuous Control Policy Gradient Methods Reinforcement Learning (RL)+1