How to Train Your Agent: Active Learning from Human Preferences and Justifications in Safety-critical Environments

Training reinforcement learning agents in real-world environments is costly, particularly for safety-critical applications. Human input can enable an agent to learn a good policy while avoiding unsafe actions, but at the cost of bothering the human with repeated queries. We present a model for safe learning in safety-critical environments from human input that minimises bother cost. Our model, JPAL-HA, proposes an efficient mechanism to harness human preferences and justifications to significantly improve safety during the learning process without increasing the number of interactions with a user. We show this with both simulation and human experiments. 1