Deep reinforcement learning (DRL) is widely used for autonomous systems including autonomous driving, robots, and drones. DRL training is essential for human-level control and adaptation to rapidly changing environments in mobile autonomous systems. However, acceleration of DRL training has three challenges: 1) large memory access, 2) various data patterns, 3) complex data dependency due to utilization of multiple DNNs. Two CMOS DRL accelerators have been proposed to support low power, high energy-efficiency DRL training in mobile autonomous systems. One accelerator solved different data patterns and large feature map memory access problems through transposable PE architecture and Top-3 experience compression. The other accelerator supports group-sparse training and integrates the on-line DRL task scheduler to support additional compression and multi DNN DRL operations for weights.