Accuracy of solar irradiance forecasting is imperative for the effective utilization and integration of solar energy into the power system. To forecast global horizontal irradiance based on a multivariate meteorological data; this study first evaluates five standalone models, including recurrent deterministic policy gradient (RDPG), long short term memory (LSTM) neural network, extreme gradient boosting (XGB), Gaussian process regression (GPR), and support vector regression (SVR). The RDPG model outperforms the standalone counterparts by demonstrating 2.485 W/m 2 , 20.591 W/m 2 , 18.316 W/m 2 , and 23.176 W/m 2 reductions in RMSE compared to the LSTM, XGB, GPR, and SVR models. Afterward, the performance of the RDPG model is further enhanced, by developing two-stage hybrid models, including improved complete ensemble empirical mode decomposition with additive noise-RDPG (ICEEMDAN-RDPG) and variational mode decomposition-RDPG (VMD-RDPG). The subsequent construction of the hybrid model ICEEMDAN-SE-VMD-RDPG (ISVR) results in the further improvement of the two-stage hybrid models. The ISVR surpasses all the established models including VMD-RDPG, ICEEMDAN-RDPG, RDPG, LSTM, XGB, GPR, and SVR by displaying 18.401 W/m 2 , 13.908 W/m 2 , 33.223 W/m 2 , 53.111 W/m 2 , 67.704 W/m 2 , 67.502 W/m 2 and 69.943 W/m 2 , respectively, decrease in RMSE. The overall results are enlightening and reveal the extension feasibility of the IVSR model for the other forecasting tasks, e.g., renewable energy integration and electrical load forecasting. INDEX TERMS Solar irradiance forecasting, decomposition techniques, sample entropy, correlation, deep reinforcement learning.