mlsanityData to 14 Oct 2026

Eval-PPO: Building an Efficient Threat Evaluator Using Proximal Policy Optimization

arXiv 2503.12098 ↗First posted 15 Mar 2025cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

In various game scenarios, selecting a fixed number of targets from multiple enemy units is an extremely challenging task. This difficulty stems from the complex relationship between the threat levels of enemy units and their feature characteristics, which complicates the design of rule-based evaluators. Moreover, traditional supervised learning methods face the challenge of lacking explicit labels during training when applied to this threat evaluation problem. In this study, we redefine the threat evaluation problem as a reinforcement learning task and introduce an efficient evaluator training algorithm, Eval-PPO, based on the Proximal Policy Optimization (PPO) algorithm. Eval-PPO integrates multidimensional enemy features and the state information of friendly units through systematic training, thereby achieving precise threat assessment. Compared with rule-based methods, Eval-PPO demonstrates a significant improvement in average success rate, with an increase of 17.84%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 11 of its 22 references that are in the map. First posted on arXiv 15 Mar 2025.

Builds on

11 of 22 references.

References · 11

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  7. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  8. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  9. 2021Counter-Strike Deathmatch with Large-Scale Behavioural Cloningcited by 50
  10. 2023Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Gamescited by 11
  11. 2023DanZero+: Dominating the GuanDan Game through Reinforcement Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reinforcement Learning-based Threat Assessment
  2. 2023Proximal Policy Optimization Actual Combat: Manipulating Output Tokenizer Length
  3. 2024Beyond the Boundaries of Proximal Policy Optimization
  4. 2026ERPPO: Entropy Regularization-based Proximal Policy Optimization
  5. 2026KLip-PPO: A per-sample KL perspective on PPO-Clip
  6. 2025Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs
  7. 2025A Practical Introduction to Deep Reinforcement Learning
  8. 2025Evaluation-Aware Reinforcement Learning