The overall goal of DeepHAC is to  advance Human-Agents Collaboration (HAC) building explainable DRL methods that enable agents to perform tasks in collaboration with humans with respect to human preferences, constraints and objectives, promoting safety and efficacy in performing collaborative tasks. The approach proposed by DeepHAC relies on three main pillars:

1. Learning collaborative policies aligned with human preferences, constraints and objectives.
2. Making policies explainable and transparent, and
3. Learning to act safely and effectively in safety-critical settings.