Reinforcement learning is currently applicable across a range of domains, including robotics, gaming, and natural language processing. However, the approach faces difficulties in environments with sparse rewards. Random network distillation (RND) is a good intrinsic reward solution to this problem. Nevertheless, the RND method’s effectiveness hinges on excellent initialization, and the reliance on random features somewhat constrains the agent’s exploration capabilities. This paper proposes a self-supervised network distillation (SSND) exploration method, addressing the drawbacks of RND’s reliance on initializing random networks while enhancing the agent’s exploration capability in sparse reward environments. The method uses distillation error as intrinsic rewards, with the target network trained using self-supervised learning. During the training of the predictor network, we noticed fluctuations in both loss values and intrinsic rewards, which have a detrimental impact on the performance of the intelligent agent. To resolve this issue, we introduce batch normalization layers to the target network, which helps mitigate intrinsic reward anomalies stemming from the target network’s instability. Experiments show that the self-supervised network distillation is better than RND in terms of exploration speed and performance.

Build scripts play an important role in transforming the source code into executable artifacts. However, the development of build scripts is typically error-prone. As one kind of the most prevalent errors in build scripts, the dependency-related errors, including missing dependencies and redundant dependencies, draw the attention of many researchers. A variety of build dependency analysis techniques have been proposed to tackle them. Unfortunately, most of these techniques, even the state-of-the-art ones, suffer from efficiency issues due to the expensive cost of monitoring the complete build process to build dynamic dependencies. Especially for large-scale projects, such the cost would not be affordable.