Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ChargingBoul: A Competitive Negotiating Agent with Novel Opponent Modeling

Joe Shymanski

TL;DR

The paper introduces ChargingBoul, a competitive negotiating agent for ANAC 2022 ANL that leverages lightweight opponent modeling (preference and strategy modeling) and two novel statistics (UBI and AUI) to classify opponents as Boulware, Hardliner, or Conceder. It uses a two-phase bidding strategy—early round Boulware-like exploration with a time-dependent utility goal and late-round drastic concessions—to maximize utility while avoiding exploitation. Results show the agent achieving second place in the official competition and top performance in unofficial runs, with strong cross-agent performance including against learning-based opponents. The study demonstrates that a compact, well-structured approach combining opponent classification and adaptive bidding can approach state-of-the-art performance in automated negotiation and suggests multiple avenues for richer modeling and real-world applicability.

Abstract

Automated negotiation has emerged as a critical area of research in multiagent systems, with applications spanning e-commerce, resource allocation, and autonomous decision-making. This paper presents ChargingBoul, a negotiating agent that competed in the 2022 Automated Negotiating Agents Competition (ANAC) and placed second in individual utility by an exceptionally narrow margin. ChargingBoul employs a lightweight yet effective strategy that balances concession and opponent modeling to achieve high negotiation outcomes. The agent classifies opponents based on bid patterns, dynamically adjusts its bidding strategy, and applies a concession policy in later negotiation stages to maximize utility while fostering agreements. We evaluate ChargingBoul's performance using competition results and subsequent studies that have utilized the agent in negotiation research. Our analysis highlights ChargingBoul's effectiveness across diverse opponent strategies and its contributions to advancing automated negotiation techniques. We also discuss potential enhancements, including more sophisticated opponent modeling and adaptive bidding heuristics, to improve its performance further.

ChargingBoul: A Competitive Negotiating Agent with Novel Opponent Modeling

TL;DR

The paper introduces ChargingBoul, a competitive negotiating agent for ANAC 2022 ANL that leverages lightweight opponent modeling (preference and strategy modeling) and two novel statistics (UBI and AUI) to classify opponents as Boulware, Hardliner, or Conceder. It uses a two-phase bidding strategy—early round Boulware-like exploration with a time-dependent utility goal and late-round drastic concessions—to maximize utility while avoiding exploitation. Results show the agent achieving second place in the official competition and top performance in unofficial runs, with strong cross-agent performance including against learning-based opponents. The study demonstrates that a compact, well-structured approach combining opponent classification and adaptive bidding can approach state-of-the-art performance in automated negotiation and suggests multiple avenues for richer modeling and real-world applicability.

Abstract

Automated negotiation has emerged as a critical area of research in multiagent systems, with applications spanning e-commerce, resource allocation, and autonomous decision-making. This paper presents ChargingBoul, a negotiating agent that competed in the 2022 Automated Negotiating Agents Competition (ANAC) and placed second in individual utility by an exceptionally narrow margin. ChargingBoul employs a lightweight yet effective strategy that balances concession and opponent modeling to achieve high negotiation outcomes. The agent classifies opponents based on bid patterns, dynamically adjusts its bidding strategy, and applies a concession policy in later negotiation stages to maximize utility while fostering agreements. We evaluate ChargingBoul's performance using competition results and subsequent studies that have utilized the agent in negotiation research. Our analysis highlights ChargingBoul's effectiveness across diverse opponent strategies and its contributions to advancing automated negotiation techniques. We also discuss potential enhancements, including more sophisticated opponent modeling and adaptive bidding heuristics, to improve its performance further.

Paper Structure

This paper contains 16 sections, 4 equations, 3 figures, 2 algorithms.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Opponent Modeling
  5. Preference Modeling
  6. Strategy Modeling
  7. UBI
  8. AUI
  9. Bidding Strategy
  10. Early Round
  11. Late Round
  12. Acceptance Strategy
  13. Results
  14. Conclusion
  15. Future Work
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Overview of ChargingBoul's entire negotiation strategy.
  • Figure 2: Default bidding strategy ($m=.5$, $E=.1$, $\epsilon=.05$).
  • Figure 3: Estimated opponent strategy ($ubi=5$) and 15% concession period.