A new Potential-Based Reward Shaping for Reinforcement Learning Agent

February 17, 2019 Β· Declared Dead Β· πŸ› Computing and Communication Workshop and Conference

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Babak Badnava, Mona Esmaeili, Nasser Mozayani, Payman Zarkesh-Ha arXiv ID 1902.06239 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 31 Venue Computing and Communication Workshop and Conference Last Checked 4 months ago
Abstract
Potential-based reward shaping (PBRS) is a particular category of machine learning methods which aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There are two steps in the process of transfer learning: extracting knowledge from previously learned tasks and transferring that knowledge to use it in a target task. The latter step is well discussed in the literature with various methods being proposed for it, while the former has been explored less. With this in mind, the type of knowledge that is transmitted is very important and can lead to considerable improvement. Among the literature of both the transfer learning and the potential-based reward shaping, a subject that has never been addressed is the knowledge gathered during the learning process itself. In this paper, we presented a novel potential-based reward shaping method that attempted to extract knowledge from the learning process. The proposed method extracts knowledge from episodes' cumulative rewards. The proposed method has been evaluated in the Arcade learning environment and the results indicate an improvement in the learning process in both the single-task and the multi-task reinforcement learner agents.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted