REVIEW 5 cited by
Emergent Coordination Through Competition
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
read the original abstract
We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based training with co-play can lead to a progression in agents' behaviors: from random, to simple ball chasing, and finally showing evidence of cooperation. Our study highlights several of the challenges encountered in large scale multi-agent training in continuous control. In particular, we demonstrate that the automatic optimization of simple shaping rewards, not themselves conducive to co-operative behavior, can lead to long-horizon team behavior. We further apply an evaluation scheme, grounded by game theoretic principals, that can assess agent performance in the absence of pre-defined evaluation tasks or human baselines.
Forward citations
Cited by 5 Pith papers
-
Expected Free Energy-based Planning as Variational Inference
EFE-based planning is formulated as variational free energy minimization with epistemic priors, decomposing into expected plan costs plus a complexity term.
-
What Type of Inference is Active Inference?
EFE-based active inference planning is characterized as VFE on an augmented model plus entropy and planning corrections, with a derived message-passing implementation and grid-world validation.
-
What Type of Inference is Active Inference?
Proper EFE-based planning is VFE plus planning and epistemic entropy corrections, realized by channel-reparameterized message passing that captures novelty.
-
Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization
Pareto UCB1 Gossip achieves O(log T) Pareto regret while Simulated NSW UCB Gossip achieves O(T^{3/4}) regret under fairness, showing the cost of the fairness constraint.
-
Arena: a toolkit for Multi-Agent Reinforcement Learning
Arena introduces a modular Interface design that extends OpenAI Gym wrappers to support complex multi-agent RL scenarios including self-play and cooperative-competitive interactions.
Discussion (0). Sign in to comment.