Safety-Aware Multi-Agent Apprenticeship Learning
This work addresses safety in multi-agent reinforcement learning, but appears incremental as it builds directly on existing single-agent methods.
The authors extended a safety-aware apprenticeship learning method from single-agent to multi-agent scenarios, extracting safe reward functions from expert behaviors and designing a novel learning framework, with empirical evaluation of the extension's performance.
Our objective of this project is to make the extension based on the technique mentioned in the paper "Safety-Aware Apprenticeship Learning" to improve the utility and the efficiency of the existing Reinforcement Learning model from a Single-Agent Learning framework to a Multi-Agent Learning framework. Our contributions to the project are presented in the following bullet points: 1. Regarding the fact that we will add an extension to the Inverse Reinforcement Learning model from a Single-Agent scenario to a Multi-Agentscenario. Our first contribution to this project is considering the case of extracting safe reward functions from expert behaviors in a Multi-Agent scenario instead of being from the Single-Agent scenario. 2. Our second contribution is extending the Single-Agent Learning Framework to a Multi-Agent Learning framework and designing a novel Learning Framework based on the extension in the end. 3. Our final contribution to this project is evaluating empirically the performance of my extension to the Single-Agent Inverse Reinforcement Learning framework.