Intelligent Trainer for Model-Based Reinforcement Learning
This addresses the problem of costly training in MBRL for researchers and practitioners, offering an incremental improvement in auto-tuning efficiency.
The paper tackles the high sampling cost and convoluted hyper-parameter tuning in model-based reinforcement learning by proposing a 'reinforcement on reinforcement' architecture that decomposes tasks into two RL layers, achieving up to 56% sampling cost savings in evaluations on OpenAI gym tasks.
Model-based reinforcement learning (MBRL) has been proposed as a promising alternative solution to tackle the high sampling cost challenge in the canonical reinforcement learning (RL), by leveraging a learned model to generate synthesized data for policy training purpose. The MBRL framework, nevertheless, is inherently limited by the convoluted process of jointly learning control policy and configuring hyper-parameters (e.g., global/local models, real and synthesized data, etc). The training process could be tedious and prohibitively costly. In this research, we propose an "reinforcement on reinforcement" (RoR) architecture to decompose the convoluted tasks into two layers of reinforcement learning. The inner layer is the canonical model-based RL training process environment (TPE), which learns the control policy for the underlying system and exposes interfaces to access states, actions and rewards. The outer layer presents an RL agent, called as AI trainer, to learn an optimal hyper-parameter configuration for the inner TPE. This decomposition approach provides a desirable flexibility to implement different trainer designs, called as "train the trainer". In our research, we propose and optimize two alternative trainer designs: 1) a uni-head trainer and 2) a multi-head trainer. Our proposed RoR framework is evaluated for five tasks in the OpenAI gym (i.e., Pendulum, Mountain Car, Reacher, Half Cheetah and Swimmer). Compared to three other baseline algorithms, our proposed Train-the-Trainer algorithm has a competitive performance in auto-tuning capability, with upto 56% expected sampling cost saving without knowing the best parameter setting in advance. The proposed trainer framework can be easily extended to other cases in which the hyper-parameter tuning is costly.