Recursive Backwards Q-Learning in Deterministic Environments

arXiv:2404.15822v1 Announce Type: cross
Abstract: Reinforcement learning is a popular method of finding optimal solutions to complex problems. Algorithms like Q-learning excel at learning to solve stochastic problems without a model of their environment. However, they take longer to solve deterministic problems than is necessary. Q-learning can be improved to better solve deterministic problems by introducing such a model-based approach. This paper introduces the recursive backwards Q-learning (RBQL) agent, which explores and builds a model of the environment. After reaching …

abstract algorithms arxiv cs.ai cs.lg environment environments excel however popular q-learning recursive reinforcement reinforcement learning solutions solve stochastic type