mlsanityData to 7 Oct 2026

Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments

arXiv 2302.14208 ↗First posted 28 Feb 2023cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning to detect, characterize and accommodate novelties is a challenge that agents operating in open-world domains need to address to be able to guarantee satisfactory task performance. Certain novelties (e.g., changes in environment dynamics) can interfere with the performance or prevent agents from accomplishing task goals altogether. In this paper, we introduce general methods and architectural mechanisms for detecting and characterizing different types of novelties, and for building an appropriate adaptive model to accommodate them utilizing logical representations and reasoning methods. We demonstrate the effectiveness of the proposed methods in evaluations performed by a third party in the adversarial multi-agent board game Monopoly. The results show high novelty detection and accommodation rates across a variety of novelty types, including changes to the rules of the game, as well as changes to the agent's action capabilities.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 50 references that are in the map. First posted on arXiv 28 Feb 2023.

Builds on

21 of 50 references.

References · 21

  1. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  2. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
  3. 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 93
  4. 2018Solving Imperfect-Information Games via Discounted Regret Minimizationcited by 68
  5. 2014Clingo = ASP + Control: Preliminary Reportcited by 56
  6. 2020Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representationscited by 32
  7. 2018Depth-Limited Solving for Imperfect-Information Gamescited by 24
  8. 2020SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learningcited by 23
  9. 2020Variational Autoencoders for Opponent Modeling in Multi-Agent Systemscited by 18
  10. 2022Symbol Guided Hindsight Priors for Reward Learning from Human Preferencescited by 8
  11. 2021Detecting and Adapting to Novelty in Gamescited by 7
  12. 2021Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approachcited by 6
9 more
  1. 2020Opponent Learning Awareness and Modelling in Multi-Objective Normal Form Gamescited by 5
  2. 2022Advice Conformance Verification by Reinforcement Learning agents for Human-in-the-Loopcited by 5
  3. 2022Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansioncited by 4
  4. 2023Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learningcited by 4
  5. 2021Computing Policies That Account For The Effects Of Human Agent Uncertainty During Execution In Markov Decision Processescited by 3
  6. 2023Data Driven Reward Initialization for Preference based Reinforcement Learningcited by 3
  7. 2023A State Augmentation based approach to Reinforcement Learning from Human Preferencescited by 2
  8. 2020Learning to Play Imperfect-Information Games by Imitating an Oracle Plannercited by 1
  9. 2021Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigmacited by 1

Built on by

Not cited yet.