Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp

Abstract

Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it's still challenging to apply it to real-world tasks, due to the poor sample efficiency. Attempting to overcome this shortcoming, several works focus on reusing the collected trajectory data during the training by decomposing them into a set of policy-irrelevant discrete transitions. However, their improvements are somewhat marginal since i) the amount of the transitions is usually small, and ii) the value assignment only happens in the joint states. To address these issues, this paper introduces a concise yet powerful method to construct Continuous Transition, which exploits the trajectory information by exploiting the potential transitions along the trajectory. Specifically, we propose to synthesize new transitions for training by linearly interpolating the consecutive transitions. To keep the constructed transitions authentic, we also develop a discriminator to guide the construction process automatically. Extensive experiments demonstrate that our proposed method achieves a significant improvement in sample efficiency on various complex continuous robotic control problems in MuJoCo and outperforms the advanced model-based / model-free RL methods. The source code is available.

References in corpus (12)

• Trust Region Policy Optimization
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Soft Actor-Critic Algorithms and Applications
• Energy-based Generative Adversarial Network
• QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
• Model-Based Reinforcement Learning for Atari
• Model-Ensemble Trust-Region Policy Optimization
• High-Performance Neural Networks for Visual Object Classification
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
• SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
• Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control