A Benchmark for Generalizing Across Diverse Team Strategies in Competitive Pokémon

• URL: http://arxiv.org/abs/2506.10326v2
• Date: Fri, 13 Jun 2025 18:31:07 GMT
• Title: A Benchmark for Generalizing Across Diverse Team Strategies in Competitive Pokémon
• Authors: Cameron Angliss, Jiaxun Cui, Jiaheng Hu, Arrasy Rahman, Peter Stone,
• Abstract summary: Pok'emon Video Game Championships (VGC) is a domain with an extraordinarily large space of possible team configurations.<n>We introduce VGC-Bench: a benchmark that provides critical infrastructure, standardizes evaluation protocols, and supplies human-play datasets.<n>In the restricted setting where an agent is trained and evaluated on a single-team configuration, our methods are able to win against a professional VGC competitor.
• Score: 31.012853711707965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Developing AI agents that can robustly adapt to dramatically different strategic landscapes without retraining is a central challenge for multi-agent learning. Pok\'emon Video Game Championships (VGC) is a domain with an extraordinarily large space of possible team configurations of approximately $10^{139}$ - far larger than those of Dota or Starcraft. The highly discrete, combinatorial nature of team building in Pok\'emon VGC causes optimal strategies to shift dramatically depending on both the team being piloted and the opponent's team, making generalization uniquely challenging. To advance research on this problem, we introduce VGC-Bench: a benchmark that provides critical infrastructure, standardizes evaluation protocols, and supplies human-play datasets and a range of baselines - from large-language-model agents and behavior cloning to reinforcement learning and empirical game-theoretic methods such as self-play, fictitious play, and double oracle. In the restricted setting where an agent is trained and evaluated on a single-team configuration, our methods are able to win against a professional VGC competitor. We extensively evaluated all baseline methods over progressively larger team sets and find that even the best-performing algorithm in the single-team setting struggles at scaling up as team size grows. Thus, policy generalization across diverse team strategies remains an open challenge for the community. Our code is open sourced at https://github.com/cameronangliss/VGC-Bench.

Related papers

• Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation [19.74776726500979]
  Adapting a single agent to a new multi-agent system brings challenges, necessitating adjustments across various tasks, environments, and interactions with unknown teammates and opponents.<n>We propose a more comprehensive setting, Agent Collaborative-Competitive Adaptation, which evaluates an agent to generalize across diverse scenarios.<n>In ACCA, agents adjust to task and environmental changes, collaborate with unseen teammates, and compete against unknown opponents.
  arXiv  Detail & Related papers  (2025-06-20T03:28:18Z)
• Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games [36.16284323379845]
  Large language models (LLMs) have been observed to suddenly exhibit advanced reasoning abilities during reinforcement learning (RL)<n>We propose Divide-Fuse-Conquer, a framework designed to enhance generalization in multi-scenario RL.
  arXiv  Detail & Related papers  (2025-05-22T08:52:21Z)
• Leading the Pack: N-player Opponent Shaping [52.682734939786464]
  We extend Opponent Shaping (OS) methods to environments involving multiple co-players and multiple shaping agents. We find that when playing with a large number of co-players, OS methods' relative performance reduces, suggesting that in the limit OS methods may not perform well.
  arXiv  Detail & Related papers  (2023-12-19T20:01:42Z)
• All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization [57.615269148301515]
  In a competitive game scenario, a set of agents have to learn decisions that maximize their goals and minimize their adversaries' goals at the same time. We propose a novel model composed of three neural layers that learn a representation of a competitive game, learn how to map the strategy of specific opponents, and how to disrupt them. Our experiments demonstrate that our model achieves better performance when playing against offline, online, and competitive-specific models, in particular when playing against the same opponent multiple times.
  arXiv  Detail & Related papers  (2023-10-02T08:11:07Z)
• Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition [3.828689444527739]
  We evaluate cooperative value-based methods in a mixed cooperative-competitive environment. We selected three training methods based on the centralised training and decentralised execution paradigm. For our experiments, we modified the StarCraft Multi-Agent Challenge environment to create competitive environments where both teams could learn and compete simultaneously.
  arXiv  Detail & Related papers  (2022-11-21T22:25:55Z)
• Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity [49.68758494467258]
  We study how to construct diverse populations of agents by carefully structuring how individuals within a population interact. Our approach is based on interaction graphs, which control the flow of information between agents during training. We provide evidence for the importance of diversity in multi-agent training and analyse the effect of applying different interaction graphs on the training trajectories, diversity and performance of populations in a range of games.
  arXiv  Detail & Related papers  (2021-10-08T11:29:52Z)
• Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition [88.26752130107259]
  In real-world multiagent systems, agents with different capabilities may join or leave without altering the team's overarching goals. We propose COPA, a coach-player framework to tackle this problem. We 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players.
  arXiv  Detail & Related papers  (2021-05-18T17:27:37Z)
• Generating Diverse and Competitive Play-Styles for Strategy Games [58.896302717975445]
  We propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes) We show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play. Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.
  arXiv  Detail & Related papers  (2021-04-17T20:33:24Z)
• Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies [37.00818384785628]
  Team members can coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game. In this setting, model-free RL methods are oftentimes unable to capture coordination because agents' policies are executed in a decentralized fashion. We show convergence to coordinated equilibria in cases where previous state-of-the-art multi-agent RL algorithms did not.
  arXiv  Detail & Related papers  (2021-02-09T18:44:16Z)
• Faster Algorithms for Optimal Ex-Ante Coordinated Collusive Strategies in Extensive-Form Zero-Sum Games [123.76716667704625]
  We focus on the problem of finding an optimal strategy for a team of two players that faces an opponent in an imperfect-information zero-sum extensive-form game. In that setting, it is known that the best the team can do is sample a profile of potentially randomized strategies (one per player) from a joint (a.k.a. correlated) probability distribution at the beginning of the game. We provide an algorithm that computes such an optimal distribution by only using profiles where only one of the team members gets to randomize in each profile.
  arXiv  Detail & Related papers  (2020-09-21T17:51:57Z)
• Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams [0.0]
  We develop a competitive multi agent environment called FortAttack in which two teams compete against each other. We observe a natural emergence of heterogeneous behavior amongst homogeneous agents when such behavior can lead to the team's success. We propose ensemble training, in which we utilize the evolved opponent strategies to train a single policy for friendly agents.
  arXiv  Detail & Related papers  (2020-07-06T22:35:56Z)

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.