Designing a perfect reward function that depicts all the aspects of the intended behavior is almost impossible, especially generalizing it outside of the training environments. Active Inverse Reward Design (AIRD) proposed the use of a series of queries, comparing possible reward functions in a single training environment. This allows the human to give information to the agent about suboptimal behaviors, in order to compute a probability distribution over the intended reward function. However, it ignores the possibility of unknown features appearing in real-world environments, and the safety measures needed until the agent completely learns the reward function. I improved this method and created Risk-averse Batch Active Inverse Reward Design (RBAIRD), which constructs batches, sets of environments the agent encounters when being used in the real world, processes them sequentially, and, for a predetermined number of iterations, asks queries that the human needs to answer for each environment of the batch. After this process is completed in one batch, the probabilities have been improved and are transferred to the next batch. This makes it capable of adapting to real-world scenarios and learning how to treat unknown features it encounters for the first time. I also integrated a risk-averse planner, similar to that of Inverse Reward Design (IRD), which samples a set of reward functions from the probability distribution and computes a trajectory that takes the most certain rewards possible. This ensures safety while the agent is still learning the reward function, and enables the use of this approach in situations where cautiousness is vital. RBAIRD outperformed the previous approaches in terms of efficiency, accuracy, and action certainty, demonstrated quick adaptability to new, unknown features, and can be more widely used for the alignment of crucial, powerful AI models.

翻译：暂无翻译