Guided Exploration in Reinforcement Learning via Monte Carlo Critic Optimization

arXiv:2206.12674v2 Announce Type: replace
Abstract: 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 …

abstract algorithms arxiv class continuous control cs.ai cs.lg current exploration exploratory noise optimization policy random reinforcement reinforcement learning solve type via