Simple random search provides a competitive approach to reinforcement learning
This work challenges assumptions in reinforcement learning for continuous control, showing that simple random search can be competitive, though it is incremental as it builds on existing benchmarks and methods.
The authors tackled the belief that random search in policy parameter space is less sample-efficient than action-space exploration by showing that their random search method matches state-of-the-art sample efficiency on MuJoCo locomotion tasks and finds a nearly optimal controller for a Linear Quadratic Regulator with unknown dynamics, being at least 15 times more computationally efficient than competing methods.
A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such beliefs by introducing a random search method for training static, linear policies for continuous control problems, matching state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks. Our method also finds a nearly optimal controller for a challenging instance of the Linear Quadratic Regulator, a classical problem in control theory, when the dynamics are not known. Computationally, our random search algorithm is at least 15 times more efficient than the fastest competing model-free methods on these benchmarks. We take advantage of this computational efficiency to evaluate the performance of our method over hundreds of random seeds and many different hyperparameter configurations for each benchmark task. Our simulations highlight a high variability in performance in these benchmark tasks, suggesting that commonly used estimations of sample efficiency do not adequately evaluate the performance of RL algorithms.