Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games
On the map: LLM agents and tool use → Reinforcement learning for LLM agents
Abstract (arXiv)
Deep reinforcement learning (DRL) has effectively enhanced gameplay experiences and game design across various game genres. However, few studies on fighting game agents have focused explicitly on enhancing player enjoyment, a critical factor for both developers and players. To address this gap and establish a practical baseline for designing enjoyability-focused agents, we propose a two-tier agent (TTA) system and conducted experiments in the classic fighting game Street Fighter II. The first tier of TTA employs a task-oriented network architecture, modularized reward functions, and hybrid training to produce diverse and skilled DRL agents. In the second tier of TTA, a Large Language Model Hyper-Agent, leveraging players' playing data and feedback, dynamically selects suitable DRL opponents. In addition, we investigate and model several key factors that affect the enjoyability of the opponent. The experiments demonstrate improvements from 64. 36% to 156. 36% in the execution of advanced skills over baseline methods. The trained agents also exhibit distinct game-playing styles. Additionally, we conducted a small-scale user study, and the overall enjoyment in the player's feedback validates the effectiveness of our TTA system.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 11 of its 31 references that are in the map. First posted on arXiv 10 Apr 2025.
Builds on
11 of 31 references.
References · 11
- 2017Attention Is All You Needcited by 59,932
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
- 2022Emergent Abilities of Large Language Modelscited by 2,483
- 2019Learning Action Representations for Reinforcement Learningcited by 75
- 2020Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabicited by 12
- 2022Where to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planningcited by 12
- 2024Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignmentcited by 7
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games
- 2025Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
- 2025Beyond Playtesting: A Generative Multi-Agent Simulation System for Massively Multiplayer Online Games
- 2025Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games
- 2024Large Language Models as Agents in Two-Player Games
- 2021Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games
- 2026COMBAT: Conditional World Models for Behavioral Agent Training
- 2026Training a Conditioned Video Game Agent on a VLM Annotated Dataset