Timezone: »

Fast Adaptation via Human Diagnosis of Task Distribution Shift
Andi Peng · Mark Ho · Aviv Netanyahu · Julie A Shah · Pulkit Agrawal

When agents fail in the world, it is important to understand why. Failures are due to underlying distribution shifts in the goals desired by the end user or to the environment layouts that impact the policy's actions. In the case of multi-task policies conditioned on goals, this problem manifests in difficulty in disambiguating between goal and policy failures: is the agent failing because it can't correctly infer what the desired goal is or because it doesn't know how to take actions toward achieving the goal? We hypothesize that successfully disentangling these two failures modes holds important implications for selecting a finetuning strategy. In this paper, we explore the feasibility of leveraging human feedback to diagnose what vs. how failures for efficient adaptation. We develop an end-to-end policy training framework that uses attention to produce a human-interpretable representation, a visual masked state, to communicate the agent's intermediate task representation. In experiments with human users in both discrete and continuous control domains, we show that our visual attention mask policy can aid participants in successfully inferring the agent's failure mode significantly better than actions alone. Leveraging this feedback, we show subsequent performance gains during finetuning and discuss implications of using humans to diagnose parameter-level failures.

Author Information

Andi Peng (MIT)
Mark Ho (New York University)
Aviv Netanyahu (MIT)
Julie A Shah (MIT)
Pulkit Agrawal (MIT)

More from the Same Authors