Deceptive Sequential Decision-Making via Regularized Policy Optimization

• URL: http://arxiv.org/abs/2501.18803v2
• Date: Wed, 20 Aug 2025 20:19:50 GMT
• Title: Deceptive Sequential Decision-Making via Regularized Policy Optimization
• Authors: Yerin Kim, Alexander Benvenuti, Bo Chen, Mustafa Karabag, Abhishek Kulkarni, Nathaniel D. Bastian, Ufuk Topcu, Matthew Hale,
• Abstract summary: We model autonomous systems as Markov decision processes, with adversaries using inverse reinforcement learning to recover reward functions.<n>We show three regularization strategies for policy synthesis problems that actively deceive an adversary about a system's reward.<n>We show that diversionary, targeted, and equivocal deception all steer the adversary to false beliefs while still attaining a total accumulated reward that is at least 97% of its optimal, non-deceptive value.
• Score: 54.38738815697299
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous systems are increasingly expected to operate in the presence of adversaries, though adversaries may infer sensitive information simply by observing a system. Therefore, present a deceptive sequential decision-making framework that not only conceals sensitive information, but actively misleads adversaries about it. We model autonomous systems as Markov decision processes, with adversaries using inverse reinforcement learning to recover reward functions. To counter them, we present three regularization strategies for policy synthesis problems that actively deceive an adversary about a system's reward. ``Diversionary deception'' leads an adversary to draw any false conclusion about the system's reward function. ``Targeted deception'' leads an adversary to draw a specific false conclusion about the system's reward function. ``Equivocal deception'' leads an adversary to infer that the real reward and a false reward both explain the system's behavior. We show how each form of deception can be implemented in policy optimization problems and analytically bound the loss in total accumulated reward induced by deception. Next, we evaluate these developments in a multi-agent setting. We show that diversionary, targeted, and equivocal deception all steer the adversary to false beliefs while still attaining a total accumulated reward that is at least 97% of its optimal, non-deceptive value.

Related papers

• Inception: Efficiently Computable Misinformation Attacks on Markov Games [14.491458698581038]
  We study security threats to Markov games due to information asymmetry and misinformation. We derive the victim's policy under worst-case rationality and present-time algorithms to compute the attacker's optimal worst-case policy. Our work exposes a security vulnerability from standard game assumptions under misinformation.
  arXiv  Detail & Related papers  (2024-06-24T20:01:43Z)
• Distributional Adversarial Loss [15.258476329309044]
  We study a new notion of adversarial loss which we call distributional adversarial loss.<n>The goal is to minimize the overall adversarial loss.<n>We show sample complexity bounds in the PAC-learning setting for our notion of adversarial loss.
  arXiv  Detail & Related papers  (2024-06-05T17:03:47Z)
• Randomized Confidence Bounds for Stochastic Partial Monitoring [8.649322557020666]
  Partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. In contextual PM, the outcomes depend on some side information that is observable by the agent before selecting the action on each round. We introduce a new class of PM strategies based on the randomization of deterministic confidence bounds.
  arXiv  Detail & Related papers  (2024-02-07T16:18:59Z)
• Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents [52.75161794035767]
  We introduce a class of bandit algorithms that meet the two objectives of performance incentivization and robustness simultaneously. We show that settings where the principal has no information about the arms' performance characteristics can be handled by combining ideas from second price auctions with our algorithms.
  arXiv  Detail & Related papers  (2023-12-13T06:54:49Z)
• Online Decision Mediation [72.80902932543474]
  Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior. In clinical diagnosis, fully-autonomous machine behavior is often beyond ethical affordances.
  arXiv  Detail & Related papers  (2023-10-28T05:59:43Z)
• Estimating and Incentivizing Imperfect-Knowledge Agents with Hidden Rewards [4.742123770879715]
  In practice, incentive providers often cannot observe the reward realizations of incentivized agents. This paper explores a repeated adverse selection game between a self-interested learning agent and a learning principal. We introduce an estimator whose only input is the history of principal's incentives and agent's choices.
  arXiv  Detail & Related papers  (2023-08-13T08:12:01Z)
• A Tale of HodgeRank and Spectral Method: Target Attack Against Rank Aggregation Is the Fixed Point of Adversarial Game [153.74942025516853]
  The intrinsic vulnerability of the rank aggregation methods is not well studied in the literature. In this paper, we focus on the purposeful adversary who desires to designate the aggregated results by modifying the pairwise data. The effectiveness of the suggested target attack strategies is demonstrated by a series of toy simulations and several real-world data experiments.
  arXiv  Detail & Related papers  (2022-09-13T05:59:02Z)
• Deceptive Planning for Resource Allocation [29.673067819076515]
  We consider a team of autonomous agents that navigate in an adversarial environment and aim to achieve a task by allocating their resources over a set of target locations. An adversary in the environment observes the autonomous team's behavior to infer their objective and responds against the team. We propose strategies for controlling the density of the autonomous team so that they can deceive the adversary.
  arXiv  Detail & Related papers  (2022-06-02T21:23:16Z)
• Admissible Policy Teaching through Reward Design [32.39785256112934]
  We study reward design strategies for incentivizing a reinforcement learning agent to adopt a policy from a set of admissible policies. The goal of the reward designer is to modify the underlying reward function cost-efficiently while ensuring that any approximately optimal deterministic policy under the new reward function is admissible.
  arXiv  Detail & Related papers  (2022-01-06T18:49:57Z)
• Identifiability in inverse reinforcement learning [0.0]
  Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem. We provide a resolution to this non-identifiability for problems with entropy regularization.
  arXiv  Detail & Related papers  (2021-06-07T10:35:52Z)
• Mutual Information State Intrinsic Control [91.38627985733068]
  Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward function. Motivated by the self-consciousness concept in psychology, we make a natural assumption that the agent knows what constitutes itself. We mathematically formalize this reward as the mutual information between the agent state and the surrounding state.
  arXiv  Detail & Related papers  (2021-03-15T03:03:36Z)
• 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)
• Maximizing Information Gain in Partially Observable Environments via Prediction Reward [64.24528565312463]
  This paper tackles the challenge of using belief-based rewards for a deep RL agent. We derive the exact error between negative entropy and the expected prediction reward. This insight provides theoretical motivation for several fields using prediction rewards.
  arXiv  Detail & Related papers  (2020-05-11T08:13:49Z)
• Intrinsic Motivation for Encouraging Synergistic Behavior [55.10275467562764]
  We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks. Our key idea is that a good guiding principle for intrinsic motivation in synergistic tasks is to take actions which affect the world in ways that would not be achieved if the agents were acting on their own.
  arXiv  Detail & Related papers  (2020-02-12T19:34:51Z)
• Corruption-robust exploration in episodic reinforcement learning [76.19192549843727]
  We study multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system. Our framework yields efficient algorithms which attain near-optimal regret in the absence of corruptions. Notably, our work provides the first sublinear regret guarantee which any deviation from purely i.i.d. transitions in the bandit-feedback model for episodic reinforcement learning.
  arXiv  Detail & Related papers  (2019-11-20T03:49:13Z)

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.