Offline safe reinforcement learning (OSRL) aims to learn policies with high rewards while satisfying safety constraints solely from data collected offline. However, the learned policies often struggle to handle states and actions that are not present or out-of-distribution (OOD) from the offline dataset, which can result in violation of the safety constraints or overly conservative behaviors during their online deployment. Moreover, many existing methods are unable to learn policies that can adapt to varying constraint thresholds. To address these challenges, we propose constraint-conditioned actor-critic (CCAC), a novel OSRL method that models the relationship between state-action distributions and safety constraints, and leverages this relationship to regularize critics and policy learning. CCAC learns policies that can effectively handle OOD data and adapt to varying constraint thresholds. Empirical evaluations on the $\texttt{DSRL}$ benchmarks show that CCAC significantly outperforms existing methods for learning adaptive, safe, and high-reward policies.

Tissue equivalent proportional counter (TEPC) is used to measure the micro-dose spectrum of ionizing radiation. Through changing tissue-equivalent gas pressure, TEPC can simulate the case of radiation energy deposition in different sizes of human cells. Various dosimetric quantities can be obtained such as absorbed dose, radiation quality factor and micro-dose equivalent. Because TEPC simulated cell size is less than the range of ionizing radiation particles, TEPC can be used as linear energy transfer spectroscopy, which can identify different linear energy transfer particles in a mixed radiation field and play an important role in mixed neutron–photon radiation field monitoring and protection. A tissue equivalent proportional counter is designed and manufactured in this paper. Through the built of micro-dose detector signal testing platform, and the realization of measurement of micro-dose detector signal debugging and important parameters (stability, energy resolution, etc.) by [Formula: see text] source method, micro-dose energy spectrum analysis and experimental measurements of Cf-252 source were ultimately achieved. Results show that the detector has good sealing performance and stability, with 12 h stability better than 2.7%. Based on all the above spectra, micro-dosing spectrum of Cf-252 source was experimentally obtained.