Corpus ID: 224705299

Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences

@article{Koster2020ModelfreeCI,
  title={Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences},
  author={R. Koster and Kevin R. McKee and Richard Everett and Laura Weidinger and William S. Isaac and Edward Hughes and Edgar A. Du{\'e}{\~n}ez-Guzm{\'a}n and T. Graepel and M. Botvinick and Joel Z. Leibo},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.09054}
}
Game theoretic views of convention generally rest on notions of common knowledge and hyper-rational models of individual behavior. However, decades of work in behavioral economics have questioned the validity of both foundations. Meanwhile, computational neuroscience has contributed a modernized 'dual process' account of decision-making where model-free (MF) reinforcement learning trades off with model-based (MB) reinforcement learning. The former captures habitual and procedural learning while… Expand
1 Citations

Figures from this paper

Grounding Artificial Intelligence in the Origins of Human Behavior
  • PDF

References

SHOWING 1-10 OF 99 REFERENCES
A multi-agent reinforcement learning model of common-pool resource appropriation
  • 80
  • PDF
Learning Existing Social Conventions via Observationally Augmented Self-Play
  • 16
Emergence of Norms through Social Learning
  • 288
  • PDF
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
  • 296
  • PDF
Beyond dichotomies in reinforcement learning
  • 7
  • PDF
Robust Multi-agent Counterfactual Prediction
  • 3
  • PDF
Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-Step Task
  • 84
  • PDF
Theory of Minds: Understanding Behavior in Groups Through Inverse Planning
  • 25
  • PDF
Learning to Be Thoughtless: Social Norms and Individual Computation
  • 220
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
  • 253
  • PDF
...
1
2
3
4
5
...