PaperActive

UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors

quality89

Updated 7 h ago · first seen 11 Sept 2026

paper_01M294FRXCBS46JJAM3VSRA5XJ

Published: 11 Sept 2026; T1 · 7 h ago
arXiv: 2512.10835; T1 · 7 h ago
Category: cs.LG; T1 · 7 h ago

Abstract

This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing approaches often require large-scale player trajectories, train separate models for different player types, or provide no direct mapping between interpretable behavioral parameters and the learned policy, limiting their scalability and controllability. We define player behavior in an N-dimensional continuous space and uniformly sample target behavior vectors from a region that encompasses the subset representing real human styles. During training, each agent receives both its current and target behavior vectors as input, and the reward is based on the normalized reduction in distance between them. This allows the policy to learn how actions influence behavioral statistics, enabling smooth control over attributes such as aggressiveness, mobility, and cooperativeness. A single PPO-based multi-agent policy can reproduce new or unseen play styles without retraining. Experiments conducted in a custom multi-player Unity game show that the proposed framework produces significantly greater behavioral diversity than a win-only baseline and reliably matches specified behavior vectors across diverse targets. The method offers a scalable solution for automated playtesting, game balancing, human-like behavior simulation, and replacing disconnected players in online games.

Authors 2

Atahan Cilan, Atay \"Ozg\"ovde

Specification

Official page: arxiv.org/abs/2512.10835
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
arXiv id: 2512.10835
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Categories: cs.LG
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
DOI: 10.1109/TG.2026.3703355
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
PDF: arxiv.org/pdf/2512.10835
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 7 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

Source tiers

T110

Freshest observation

7 h ago

Conflicts

None

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

10 claims · 10 properties

Official pageofficial_url1

Claim history for Official page
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/abs/2512.10835	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Abstractabstract1

Claim history for Abstract
Value	Valid from → to	Status	Source	Confidence	Extractor
This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing approaches often require large-scale player trajectories, train separate models for different player types, or provide no direct mapping between interpretable behavioral parameters and the learned policy, limiting their scalability and controllability. We define player behavior in an N-dimensional continuous space and uniformly sample target behavior vectors from a region that encompasses the subset representing real human styles. During training, each agent receives both its current and target behavior vectors as input, and the reward is based on the normalized reduction in distance between them. This allows the policy to learn how actions influence behavioral statistics, enabling smooth control over attributes such as aggressiveness, mobility, and cooperativeness. A single PPO-based multi-agent policy can reproduce new or unseen play styles without retraining. Experiments conducted in a custom multi-player Unity game show that the proposed framework produces significantly greater behavioral diversity than a win-only baseline and reliably matches specified behavior vectors across diverse targets. The method offers a scalable solution for automated playtesting, game balancing, human-like behavior simulation, and replacing disconnected players in online games.	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Arxiv announce typearxiv_announce_type1

Claim history for Arxiv announce type
Value	Valid from → to	Status	Source	Confidence	Extractor
replace	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

arXiv idarxiv_id1

Claim history for arXiv id
Value	Valid from → to	Status	Source	Confidence	Extractor
2512.10835	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Authorsauthors1

Claim history for Authors
Value	Valid from → to	Status	Source	Confidence	Extractor
Atahan Cilan, Atay \"Ozg\"ovde	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Categoriescategories1

Claim history for Categories
Value	Valid from → to	Status	Source	Confidence	Extractor
cs.LG	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

DOIdoi1

Claim history for DOI
Value	Valid from → to	Status	Source	Confidence	Extractor
10.1109/TG.2026.3703355	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

PDFpdf_url1

Claim history for PDF
Value	Valid from → to	Status	Source	Confidence	Extractor
https://arxiv.org/pdf/2512.10835	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Primary categoryprimary_category1

Claim history for Primary category
Value	Valid from → to	Status	Source	Confidence	Extractor
cs.LG	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Publishedpublished_at1

Claim history for Published
Value	Valid from → to	Status	Source	Confidence	Extractor
11 Sept 2026	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.LG	feed	T1· Official	5 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.