Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization
This addresses the need for more effective and adaptive exploration in continuous control tasks, offering a domain-specific improvement over existing methods.
The paper tackled the problem of inefficient exploration in deep deterministic off-policy reinforcement learning algorithms by proposing a guided exploration method using an ensemble of Monte Carlo Critics, resulting in superior performance on various DMControl suite problems.
The class of deep deterministic off-policy algorithms is effectively applied to solve challenging continuous control problems. Current approaches commonly utilize random noise as an exploration method, which has several drawbacks, including the need for manual adjustment for a given task and the absence of exploratory calibration during the training process. We address these challenges by proposing a novel guided exploration method that uses an ensemble of Monte Carlo Critics for calculating exploratory action correction. The proposed method enhances the traditional exploration scheme by dynamically adjusting exploration. Subsequently, we present a novel algorithm that leverages the proposed exploratory module for both policy and critic modification. The presented algorithm demonstrates superior performance compared to modern reinforcement learning algorithms across a variety of problems in the DMControl suite.