Normative Disagreement as a Challenge for Cooperative AI

• URL: http://arxiv.org/abs/2111.13872v1
• Date: Sat, 27 Nov 2021 11:37:42 GMT
• Title: Normative Disagreement as a Challenge for Cooperative AI
• Authors: Julian Stastny, Maxime Rich\'e, Alexander Lyzhov, Johannes Treutlein, Allan Dafoe, Jesse Clifton
• Abstract summary: We argue that typical cooperation-inducing learning algorithms fail to cooperate in bargaining problems. We develop a class of norm-adaptive policies and show in experiments that these significantly increase cooperation.
• Score: 56.34005280792013
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cooperation in settings where agents have both common and conflicting interests (mixed-motive environments) has recently received considerable attention in multi-agent learning. However, the mixed-motive environments typically studied have a single cooperative outcome on which all agents can agree. Many real-world multi-agent environments are instead bargaining problems (BPs): they have several Pareto-optimal payoff profiles over which agents have conflicting preferences. We argue that typical cooperation-inducing learning algorithms fail to cooperate in BPs when there is room for normative disagreement resulting in the existence of multiple competing cooperative equilibria, and illustrate this problem empirically. To remedy the issue, we introduce the notion of norm-adaptive policies. Norm-adaptive policies are capable of behaving according to different norms in different circumstances, creating opportunities for resolving normative disagreement. We develop a class of norm-adaptive policies and show in experiments that these significantly increase cooperation. However, norm-adaptiveness cannot address residual bargaining failure arising from a fundamental tradeoff between exploitability and cooperative robustness.

Related papers

• Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactions [8.96091816092671]
  We propose a novel framework called emphRole Play (RP) RP employs role embeddings to transform the challenge of policy diversity into a more manageable diversity of roles. It trains a common policy with role embedding observations and employs a role predictor to estimate the joint role embeddings of other agents, helping the learning agent adapt to its assigned role.
  arXiv  Detail & Related papers  (2024-11-02T07:25:48Z)
• Learning and Sustaining Shared Normative Systems via Bayesian Rule Induction in Markov Games [2.307051163951559]
  We build learning agents that cooperate flexibly with the human institutions they are embedded in. By assuming shared norms, a newly introduced agent can infer the norms of an existing population from observations of compliance and violation. Since agents can bootstrap common knowledge of the norms, this leads the norms to be widely adhered to, enabling new entrants to rapidly learn those norms.
  arXiv  Detail & Related papers  (2024-02-20T21:58:40Z)
• Policy Diversity for Cooperative Agents [8.689289576285095]
  Multi-agent reinforcement learning aims to find the optimal team cooperative policy to complete a task. There may exist multiple different ways of cooperating, which usually are very needed by domain experts. Unfortunately, there is a general lack of effective policy diversity approaches specifically designed for the multi-agent domain.
  arXiv  Detail & Related papers  (2023-08-28T05:23:16Z)
• Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning [48.41925886860991]
  Real-world cooperation often requires intensive coordination among agents simultaneously. Traditional methods that learn the value function as a monotonic mixing of per-agent utilities cannot solve the tasks with non-monotonic returns. We propose a novel explicit credit assignment method to address the non-monotonic problem.
  arXiv  Detail & Related papers  (2023-02-14T07:23:59Z)
• Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning [71.53769213321202]
  We formalize the notions of coordination level and heterogeneity level of an environment. We present HECOGrid, a suite of multi-agent environments that facilitates empirical evaluation of different MARL approaches. We propose a Training Decentralized Execution learning approach that enables agents to work efficiently in high-coordination and high-heterogeneity environments.
  arXiv  Detail & Related papers  (2022-10-04T18:17:01Z)
• Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming [0.0]
  We show that reformulating an agent's policy to be conditional on the policies of its teammates inherently maximizes Mutual Information (MI) lower-bound when optimizing under Policy Gradient (PG) Our approach, InfoPG, outperforms baselines in learning emergent collaborative behaviors and sets the state-of-the-art in decentralized cooperative MARL tasks.
  arXiv  Detail & Related papers  (2022-01-20T22:54:32Z)
• Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments [4.705291741591329]
  Mixed environments are notorious for the conflicts of selfish and social interests. We propose BAROCCO to balance individual and social incentives. Our meta-algorithm is compatible with both Q-learning and Actor-Critic frameworks.
  arXiv  Detail & Related papers  (2021-02-24T14:35:32Z)
• Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition [52.06086375833474]
  Non-stationarity is one thorny issue in multi-agent reinforcement learning. We introduce a $delta$-stationarity measurement to explicitly model the stationarity of a policy sequence. We propose a trust region decomposition network based on message passing to estimate the joint policy divergence.
  arXiv  Detail & Related papers  (2021-02-21T14:46:50Z)
• UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning [53.73686229912562]
  We propose a novel MARL approach called Universal Value Exploration (UneVEn) UneVEn learns a set of related tasks simultaneously with a linear decomposition of universal successor features. Empirical results on a set of exploration games, challenging cooperative predator-prey tasks requiring significant coordination among agents, and StarCraft II micromanagement benchmarks show that UneVEn can solve tasks where other state-of-the-art MARL methods fail.
  arXiv  Detail & Related papers  (2020-10-06T19:08:47Z)
• Non-local Policy Optimization via Diversity-regularized Collaborative Exploration [45.997521480637836]
  We propose a novel non-local policy optimization framework called Diversity-regularized Collaborative Exploration (DiCE) DiCE utilizes a group of heterogeneous agents to explore the environment simultaneously and share the collected experiences. We implement the framework in both on-policy and off-policy settings and the experimental results show that DiCE can achieve substantial improvement over the baselines.
  arXiv  Detail & Related papers  (2020-06-14T03:31:11Z)

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.