The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability

• URL: http://arxiv.org/abs/2506.09940v1
• Date: Wed, 11 Jun 2025 17:06:57 GMT
• Title: The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
• Authors: Jiachen Hu, Rui Ai, Han Zhong, Xiaoyu Chen, Liwei Wang, Zhaoran Wang, Zhuoran Yang,
• Abstract summary: Information asymmetry is a pervasive feature of multi-agent systems.<n>This paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer?<n>We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning.
• Score: 93.11220429350278
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Information asymmetry is a pervasive feature of multi-agent systems, especially evident in economics and social sciences. In these settings, agents tailor their actions based on private information to maximize their rewards. These strategic behaviors often introduce complexities due to confounding variables. Simultaneously, knowledge transportability poses another significant challenge, arising from the difficulties of conducting experiments in target environments. It requires transferring knowledge from environments where empirical data is more readily available. Against these backdrops, this paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer? We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning, framed within an online strategic interaction model. Our method provably achieves learning of an $\epsilon$-optimal policy with a tight sample complexity of $O(1/\epsilon^2)$.

Related papers

• FAST: Similarity-based Knowledge Transfer for Efficient Policy Learning [57.4737157531239]
  Transfer Learning offers the potential to accelerate learning by transferring knowledge across tasks.<n>It faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source policies.<n>In this work we challenge the key issues in TL to improve knowledge transfer, agents performance across tasks and reduce computational costs.
  arXiv  Detail & Related papers  (2025-07-27T22:21:53Z)
• Agentic Knowledgeable Self-awareness [79.25908923383776]
  KnowSelf is a data-centric approach that applies agents with knowledgeable self-awareness like humans.<n>Our experiments demonstrate that KnowSelf can outperform various strong baselines on different tasks and models with minimal use of external knowledge.
  arXiv  Detail & Related papers  (2025-04-04T16:03:38Z)
• Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients [60.22876915395139]
  This paper studies a challenging robust federated learning task with model heterogeneous and data corrupted clients.<n>Data corruption is unavoidable due to factors such as random noise, compression artifacts, or environmental conditions in real-world deployment.<n>We propose a novel Robust Asymmetric Heterogeneous Federated Learning framework to address these issues.
  arXiv  Detail & Related papers  (2025-03-12T09:52:04Z)
• LEKA:LLM-Enhanced Knowledge Augmentation [24.552995956148145]
  Humans excel in analogical learning and knowledge transfer.<n>Models would transition from passively acquiring to actively accessing and learning from knowledge.<n>We develop a knowledge augmentation method LEKA for knowledge transfer.
  arXiv  Detail & Related papers  (2025-01-29T17:44:57Z)
• Knowledge Transfer for Cross-Domain Reinforcement Learning: A Systematic Review [2.94944680995069]
  Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. By reusing knowledge from a different task, knowledge transfer methods present an alternative to reduce the training time in RL. This review presents a unifying analysis of methods focused on transferring knowledge across different domains.
  arXiv  Detail & Related papers  (2024-04-26T20:36:58Z)
• Knowledge is reward: Learning optimal exploration by predictive reward cashing [5.279475826661643]
  We exploit the inherent mathematical structure of Bayes-adaptive problems in order to dramatically simplify the problem. The key to this simplification comes from the novel concept of cross-value. This results in a new denser reward structure that "cashes in" all future rewards that can be predicted from the current information state.
  arXiv  Detail & Related papers  (2021-09-17T12:52:24Z)
• IQ-Learn: Inverse soft-Q Learning for Imitation [95.06031307730245]
  imitation learning from a small amount of expert data can be challenging in high-dimensional environments with complex dynamics. Behavioral cloning is a simple method that is widely used due to its simplicity of implementation and stable convergence. We introduce a method for dynamics-aware IL which avoids adversarial training by learning a single Q-function.
  arXiv  Detail & Related papers  (2021-06-23T03:43:10Z)
• Tree of Knowledge: an Online Platform for Learning the Behaviour of Complex Systems [0.0]
  TreeOfKnowledge implements a new methodology specifically designed for learning complex behaviours from complex systems. It learns agent behaviour from many heterogenous datasets and can learn from these datasets even if the phenomenon of interest is not directly observed.
  arXiv  Detail & Related papers  (2021-02-27T19:39:14Z)
• Latent Skill Planning for Exploration and Transfer [49.25525932162891]
  In this paper, we investigate how these two approaches can be integrated into a single reinforcement learning agent. We leverage the idea of partial amortization for fast adaptation at test time. We demonstrate the benefits of our design decisions across a suite of challenging locomotion tasks.
  arXiv  Detail & Related papers  (2020-11-27T18:40:03Z)

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.