Exploration Strategy based on Validity of Actions in Deep Reinforcement Learning
Hyung-Suk Yoon,Sang-Hyun Lee,Seung-Woo Seo,Hyung-Suk Yoon,Sang-Hyun Lee,Seung-Woo Seo
How to explore environments is one of the most critical factors for the performance of an agent in reinforcement learning. Conventional exploration strategies such as ε-greedy algorithm and Gaussian exploration noise simply depend on pure randomness. However, it is required for an agent to consider its training progress and long-term usefulness of actions to efficiently explore complex environment...
