mlsanityData to 7 Oct 2026

All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization

arXiv 2310.00964 ↗First posted 2 Oct 2023cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In a competitive game scenario, a set of agents have to learn decisions that maximize their goals and minimize their adversaries' goals at the same time. Besides dealing with the increased dynamics of the scenarios due to the opponents' actions, they usually have to understand how to overcome the opponent's strategies. Most of the common solutions, usually based on continual learning or centralized multi-agent experiences, however, do not allow the development of personalized strategies to face individual opponents. In this paper, we propose a novel model composed of three neural layers that learn a representation of a competitive game, learn how to map the strategy of specific opponents, and how to disrupt them. The entire model is trained online, using a composed loss based on a contrastive optimization, to learn competitive and multiplayer games. We evaluate our model on a pokemon duel scenario and the four-player competitive Chef's Hat card game. Our experiments demonstrate that our model achieves better performance when playing against offline, online, and competitive-specific models, in particular when playing against the same opponent multiple times. We also present a discussion on the impact of our model, in particular on how well it deals with on specific strategy learning for each of the two scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 2 Oct 2023.

Builds on

31 of 51 references.

References · 31

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  7. 2016Generative Adversarial Imitation Learningcited by 1,576
  8. 2018Experience Replay for Continual Learningcited by 1,074
  9. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  10. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  11. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  12. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
19 more
  1. 2018Reinforced Continual Learningcited by 186
  2. 2016Sample Efficient Actor-Critic with Experience Replaycited by 185
  3. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  4. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
  5. 2019A continual learning survey: Defying forgetting in classification taskscited by 118
  6. 2020Uncovering the structure of clinical EEG signals with self-supervised learningcited by 109
  7. 2017Third-Person Imitation Learningcited by 103
  8. 2018Multi-Agent Generative Adversarial Imitation Learningcited by 99
  9. 2016Opponent Modeling in Deep Reinforcement Learningcited by 94
  10. 2018Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgettingcited by 46
  11. 2019Imitation Learning for Human Pose Predictioncited by 44
  12. 2018StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learningcited by 25
  13. 2018Deep Reinforcement Learning for General Video Game AIcited by 25
  14. 2018Deep Generative Models with Learnable Knowledge Constraintscited by 23
  15. 2020Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimizationcited by 22
  16. 2016Personalizing a Dialogue System with Transfer Reinforcement Learningcited by 17
  17. 2018Visual Transfer between Atari Games using Competitive Reinforcement Learningcited by 5
  18. 2020Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Gamecited by 3
  19. 2020Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancementcited by 3

Built on by

Not cited yet.