Learning the Preferences of a Learning Agent

• URL: http://arxiv.org/abs/2605.09217v1
• Date: Sat, 09 May 2026 23:28:22 GMT
• Title: Learning the Preferences of a Learning Agent
• Abstract summary: inverse reinforcement learning aims to develop methods that allow for inferring preferences from observed behavior.<n>In this paper, we formalize the problem of learning the preferences of a learning agent.<n>We establish theoretical guarantees for various preference learning algorithms, or otherwise show that such guarantees are impossible.
• Score: 11.820109078997504
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcement learning (IRL) aims to develop methods that allow for inferring preferences from observed behavior. However, IRL assumes the human to be approximately optimal. This is a big limitation in cases where the human themselves may be learning to act optimally in an environment. In this paper, we formalize the problem of learning the preferences of a learning agent: a predictor observes a learner acting online and tries to infer the underlying reward function being (initially suboptimally) optimized by the learner. We model the learner as either being no-regret, or as converging to an optimal Boltzmann policy over time. In each of these settings, we establish theoretical guarantees for various preference learning algorithms, or otherwise show that such guarantees are impossible.

Related papers

• Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning [12.742158403867002]
  Reinforcement Learning from Human Feedback is a powerful paradigm for aligning foundation models to human values and preferences. Current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. We develop a class of multimodal RLHF methods to address the need for pluralistic alignment.
  arXiv  Detail & Related papers  (2024-08-19T15:18:30Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• Contrastive Preference Learning: Learning from Human Feedback without RL [71.77024922527642]
  We introduce Contrastive Preference Learning (CPL), an algorithm for learning optimal policies from preferences without learning reward functions. CPL is fully off-policy, uses only a simple contrastive objective, and can be applied to arbitrary MDPs.
  arXiv  Detail & Related papers  (2023-10-20T16:37:56Z)
• Reinforcement Learning from Diverse Human Preferences [68.4294547285359]
  This paper develops a method for crowd-sourcing preference labels and learning from diverse human preferences. The proposed method is tested on a variety of tasks in DMcontrol and Meta-world. It has shown consistent and significant improvements over existing preference-based RL algorithms when learning from diverse feedback.
  arXiv  Detail & Related papers  (2023-01-27T15:18:54Z)
• Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience [89.30876995059168]
  inverse reinforcement learning (IRL) -- inferring the reward function of an agent from observing its behavior. This paper addresses the problem of IRL -- inferring the reward function of an agent from observing its behavior.
  arXiv  Detail & Related papers  (2022-08-09T17:29:49Z)
• Strategizing against Learners in Bayesian Games [74.46970859427907]
  We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy. We consider general Bayesian games, where the payoffs of both the payoffs of both the learner and the learner could depend on the type.
  arXiv  Detail & Related papers  (2022-05-17T18:10:25Z)
• Privacy-Preserving Reinforcement Learning Beyond Expectation [6.495883501989546]
  Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. It is important to align system (or agent) behaviors with the preferences of one or more human users. We consider the case when an agent has to learn behaviors in an unknown environment.
  arXiv  Detail & Related papers  (2022-03-18T21:28:29Z)
• The Information Geometry of Unsupervised Reinforcement Learning [133.20816939521941]
  Unsupervised skill discovery is a class of algorithms that learn a set of policies without access to a reward function. We show that unsupervised skill discovery algorithms do not learn skills that are optimal for every possible reward function.
  arXiv  Detail & Related papers  (2021-10-06T13:08:36Z)
• Exploration and preference satisfaction trade-off in reward-free learning [3.4998703934432682]
  We introduce a model-based Bayesian agent equipped with a preference learning mechanism using conjugate priors. We illustrate this in the OpenAI Gym FrozenLake and the 3D mini-world environments -- with and without volatility. Our experiments suggest that learnable (reward-free) preferences entail a trade-off between exploration and preference satisfaction.
  arXiv  Detail & Related papers  (2021-06-08T13:24:58Z)

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.