Neupl: Neural Population Learning

Abstract

Learning in strategy games (e.g. StarCraft, poker) requires the discovery of diverse policies. This is often achieved by iteratively training new policies against existing ones, growing a policy population that is robust to exploit. This iterative approach suffers from two issues in real-world games: a) under finite budget, approximate best-response operators at each iteration needs truncating, resulting in under-trained good-responses populating the population; b) repeated learning of basic skills at each iteration is wasteful and becomes intractable in the presence of increasingly strong opponents. In this work, we propose Neural Population Learning (NeuPL) as a solution to both issues. NeuPL offers convergence guarantees to a population of best-responses under mild assumptions. By representing a population of policies within a single conditional model, NeuPL enables transfer learning across policies. Empirically, we show the generality, improved performance and efficiency of NeuPL a

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2022neupl

Related papers

• Neural Population Learning Beyond Symmetric Zero-sum Games (2024)0.00
• Simplex Neural Population Learning: Any-mixture Bayes-optimality In Symmetric Zero-sum Games (2022)0.00
• Policyevolve: Evolving Programmatic Policies By Llms For Multi-player Games Via Population-based Training (2025)0.00
• A Generalized Training Approach For Multiagent Learning (2019)0.00
• Neural Auto-curricula (2021)0.00
• Learning To Play No-press Diplomacy With Best Response Policy Iteration (2020)0.00
• Neuro-algorithmic Policies Enable Fast Combinatorial Generalization (2021)0.00
• Episodic Exploration For Deep Deterministic Policies: An Application To Starcraft Micromanagement Tasks (2016)0.00