Broad Critic Deep Actor Reinforcement Learning for Continuous Control
This work addresses computational efficiency for real-time control applications, but it is incremental as it enhances existing methods.
The paper tackles the high data and computational demands of deep reinforcement learning in continuous control by introducing a hybrid actor-critic framework that combines broad learning systems with deep neural networks, resulting in improved training efficiency and accuracy across three algorithms.
In the domain of continuous control, deep reinforcement learning (DRL) demonstrates promising results. However, the dependence of DRL on deep neural networks (DNNs) results in the demand for extensive data and increased computational cost. To address this issue, a novel hybrid actor-critic reinforcement learning (RL) framework is introduced. The proposed framework integrates the broad learning system (BLS) with DNN, aiming to merge the strengths of both distinct architectural paradigms. Specifically, the critic network employs BLS for rapid value estimation via ridge regression, while the actor network retains the DNN structure to optimize policy gradients. This hybrid design is generalizable and can enhance existing actor-critic algorithms. To demonstrate its versatility, the proposed framework is integrated into three widely used actor-critic algorithms -- deep deterministic policy gradient (DDPG), soft actor-critic (SAC), and twin delayed DDPG (TD3), resulting in BLS-augmented variants. Experimental results reveal that all BLS-enhanced versions surpass their original counterparts in terms of training efficiency and accuracy. These improvements highlight the suitability of the proposed framework for real-time control scenarios, where computational efficiency and rapid adaptation are critical.