Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response

• URL: http://arxiv.org/abs/2607.27508v1
• Date: Wed, 29 Jul 2026 22:49:28 GMT
• Title: Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response
• Abstract summary: We propose a class of assistance games in which pragmatic-pedagogic reasoning resolves goal uncertainty in a single time step.<n>Within this class, we show that mainstream inverse optimal control exhibits an inference ceiling that hinders alignment.<n>We validate our theoretical results and proposed method on a simple collaborative block-building example.
• Score: 0.25066242154596113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Assistance games formalize human-robot collaboration under asymmetric information: the human knows the goal, while the robot must infer it from observation and interaction in order to assist effectively. In general, computing optimal assistance game strategies online is intractable, since exact solutions require planning in a POMDP. We identify a class of assistance games in which pragmatic-pedagogic reasoning resolves goal uncertainty in a single time step, rendering the full-horizon game exactly solvable by a tractable best-response procedure. Within this class, we show that mainstream inverse optimal control exhibits an inference ceiling that hinders alignment, while pragmatic-pedagogic reasoning overcomes this barrier by immediately disambiguating goals through actions that look equivalent under task execution alone. Finally, we validate our theoretical results and proposed method on a simple collaborative block-building example.

Related papers

• Learning to Assist Humans without Inferring Rewards [65.28156318196397]
  We build upon prior work that studies assistance through the lens of empowerment.<n>An assistive agent aims to maximize the influence of the human's actions.<n>We prove that these representations estimate a similar notion of empowerment to that studied by prior work.
  arXiv  Detail & Related papers  (2024-11-04T21:31:04Z)
• Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games [34.34801907296059]
  In human-AI interaction, a prominent goal is to attain humans desirable outcome with the assistance of AI agents. We employ a theoretical framework called structural causal game (SCG) to formalize the human-AI interactive process. We introduce a strategy referred to as pre-policy intervention on the SCG to steer AI agents towards attaining the humans desirable outcome.
  arXiv  Detail & Related papers  (2024-05-26T14:42:49Z)
• Optimising Human-AI Collaboration by Learning Convincing Explanations [62.81395661556852]
  We propose a method for a collaborative system that remains safe by having a human making decisions. Ardent enables efficient and effective decision-making by adapting to individual preferences for explanations.
  arXiv  Detail & Related papers  (2023-11-13T16:00:16Z)
• Scalable Learning of Intrusion Responses through Recursive Decomposition [0.0]
  We study automated intrusion response for an IT infrastructure and the interaction between an attacker and a defender as a partially observed game. To solve the game we follow an approach where attack and defense strategies co-evolve through reinforcement learning and self-play toward an equilibrium. We introduce an algorithm called Decompositional Fictitious Self-Play (DFSP), which learns equilibria through approximation.
  arXiv  Detail & Related papers  (2023-09-06T18:12:07Z)
• NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants [79.27554831580309]
  We study how to build socially intelligent robots to assist people in their homes. We focus on assistance with online goal inference, where robots must simultaneously infer humans' goals.
  arXiv  Detail & Related papers  (2023-01-12T18:59:34Z)
• Outcome-Driven Reinforcement Learning via Variational Inference [95.82770132618862]
  We discuss a new perspective on reinforcement learning, recasting it as the problem of inferring actions that achieve desired outcomes, rather than a problem of maximizing rewards. To solve the resulting outcome-directed inference problem, we establish a novel variational inference formulation that allows us to derive a well-shaped reward function. We empirically demonstrate that this method eliminates the need to design reward functions and leads to effective goal-directed behaviors.
  arXiv  Detail & Related papers  (2021-04-20T18:16:21Z)
• End-to-End Learning and Intervention in Games [60.41921763076017]
  We provide a unified framework for learning and intervention in games. We propose two approaches, respectively based on explicit and implicit differentiation. The analytical results are validated using several real-world problems.
  arXiv  Detail & Related papers  (2020-10-26T18:39:32Z)
• Extending the Hint Factory for the assistance dilemma: A novel, data-driven HelpNeed Predictor for proactive problem-solving help [6.188683567894372]
  We present a set of data-driven methods to classify, predict, and prevent unproductive problem-solving steps. We present a HelpNeed classification, that uses prior student data to determine when students are likely to be unproductive. We conclude with suggestions on how these HelpNeed methods could be applied in other well-structured open-ended domains.
  arXiv  Detail & Related papers  (2020-10-08T17:04:03Z)
• AvE: Assistance via Empowerment [77.08882807208461]
  We propose a new paradigm for assistance by instead increasing the human's ability to control their environment. This task-agnostic objective preserves the person's autonomy and ability to achieve any eventual state.
  arXiv  Detail & Related papers  (2020-06-26T04:40:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.