mlsanityData to 14 Oct 2026

Reflection of Episodes: Learning to Play Game from Expert and Self Experiences

arXiv 2502.13388 ↗First posted 19 Feb 2025cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

StarCraft II is a complex and dynamic real-time strategy (RTS) game environment, which is very suitable for artificial intelligence and reinforcement learning research. To address the problem of Large Language Model(LLM) learning in complex environments through self-reflection, we propose a Reflection of Episodes(ROE) framework based on expert experience and self-experience. This framework first obtains key information in the game through a keyframe selection method, then makes decisions based on expert experience and self-experience. After a game is completed, it reflects on the previous experience to obtain new self-experience. Finally, in the experiment, our method beat the robot under the Very Hard difficulty in TextStarCraft II. We analyze the data of the LLM in the process of the game in detail, verified its effectiveness.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 9 of its 37 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

9 of 37 references.

References · 9

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  2. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  3. 2023PaLM 2 Technical Reportcited by 1,162
  4. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  5. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  6. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  7. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 274
  8. 2024Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimizationcited by 94
  9. 2022On Efficient Reinforcement Learning for Full-length Game of StarCraft IIcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026GameVerse: Can Vision-Language Models Learn from Video-based Reflection?cited by 8
  2. 2026Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiversecited by 3
  3. 2025Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generationcited by 1
  4. 2025LLM-Cave: A benchmark and light environment for large language models reasoning and decision-making systemcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach
  2. 2025SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks
  3. 2026Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
  4. 2026World Models for Policy Refinement in StarCraft II
  5. 2024SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models
  6. 2026Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios
  7. 2020TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
  8. 2023SPRING: Studying the Paper and Reasoning to Play Games