REVIEW 7 cited by
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Multi-agent Reinforcement Learning in Sequential Social Dilemmas
read the original abstract
Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Cooperativeness is a property that applies to policies, not elementary actions. We introduce sequential social dilemmas that share the mixed incentive structure of matrix game social dilemmas but also require agents to learn policies that implement their strategic intentions. We analyze the dynamics of policies learned by multiple self-interested independent learning agents, each using its own deep Q-network, on two Markov games we introduce here: 1. a fruit Gathering game and 2. a Wolfpack hunting game. We characterize how learned behavior in each domain changes as a function of environmental factors including resource abundance. Our experiments show how conflict can emerge from competition over shared resources and shed light on how the sequential nature of real world social dilemmas affects cooperation.
Forward citations
Cited by 7 Pith papers
-
The Reciprocity Gradient
The reciprocity gradient allows agents to learn near-optimal context-sensitive policies by analytically propagating reward gradients through reputation chains in multi-agent settings.
-
Unsupervised Causal Abstractions Discovery
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
-
Investigating the Impact of Subgraph Social Structure Preference on the Strategic Behavior of Networked Mixed-Motive Learning Agents
Preferences over local subgraph structures cause distinct changes in reward collection and strategic actions for agents playing sequential social dilemmas in Harvest and Cleanup environments.
-
Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
-
Memory-Induced Supra-Competitive Outcomes Between Deep Reinforcement Learning Agents in Optimal Trade Execution
In a two-agent Almgren-Chriss liquidation game, deep RL agents given intra-episode history of prices and own actions achieve supra-competitive outcomes more frequently and persistently than agents without such memory.
-
Learning Incentive Structures for Cooperative Resilience in Multi-Agent Systems under Social Dilemmas
A method infers resilience-promoting reward functions via trajectory scoring and integrates them into MARL, with hybrid incentives shown to reduce collapse in disrupted resource environments.
-
AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks
AI researchers must lead technical research in arms control to mitigate risks from military AI systems, drawing lessons from nuclear deterrence.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.