A Novel State Space Exploration Method for the Sparse-Reward Reinforcement Learning Environment
(2023)
Presentation / Conference Contribution
Liu, X., Ma, L., Chen, Z., Zheng, C., Chen, R., Liao, Y., & Yang, S. (2023, December). A Novel State Space Exploration Method for the Sparse-Reward Reinforcement Learning Environment. Presented at 43rd SGAI International Conference on Artificial Intelligence, Cambridge, UK
Sparse-reward reinforcement learning environments pose a particular challenge because the agent receives infrequent rewards, making it difficult to learn an optimal policy. In this paper, we propose NSSE, a novel approach that combines that stratifie... Read More about A Novel State Space Exploration Method for the Sparse-Reward Reinforcement Learning Environment.