Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
This work addresses the poor sample efficiency in deep reinforcement learning, which is a critical bottleneck for applying RL to real-world robotic control tasks. It offers an incremental improvement to existing methods.
This paper tackles the problem of poor sample efficiency in deep reinforcement learning for continuous control tasks. It proposes a method to synthesize new transitions by linearly interpolating consecutive transitions and uses a discriminator to ensure authenticity. The method achieves significant improvements in sample efficiency on various MuJoCo robotic control problems, outperforming advanced model-based and model-free RL methods.
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.