Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents

CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories

This paper proposes a novel deep reinforcement learning algorithm to perform automatic analysis and detection of gameplay issues in complex 3D navigation environments. The Curiosity-Conditioned Proximal Trajectories (CCPT) method combines curiosity and imitation learning to train agents to methodically explore in the proximity of known trajectories derived from expert demonstrations. We show how CCPT can explore complex environments, discover gameplay issues and design oversights in the process, and recognize and highlight them directly to game designers. We further demonstrate the effectivene…

面向大语言模型的好奇心驱动红队测试

Curiosity-driven Red-teaming for Large Language Models

针对强化学习红队方法生成有效攻击提示覆盖不足的问题，本文引入好奇心驱动探索，提出 CRT，在保持或提升攻击有效性的同时扩大测试用例覆盖，并成功诱发经人类偏好微调的 LLaMA2 产生有毒回复。

Semantic Curiosity for Active Visual Learning

In this paper, we study the task of embodied interactive learning for object detection. Given a set of environments (and some labeling budget), our goal is to learn an object detector by having an agent select what data to obtain labels for. How should an exploration policy decide which trajectory should be labeled? One possibility is to use a trained object detector's failure cases as an external reward. However, this will require labeling millions of frames required for training RL policies, which is infeasible. Instead, we explore a self-supervised approach for training our exploration poli…

CAMEO: Curiosity Augmented Metropolis for Exploratory Optimal Policies

Reinforcement Learning has drawn huge interest as a tool for solving optimal control problems. Solving a given problem (task or environment) involves converging towards an optimal policy. However, there might exist multiple optimal policies that can dramatically differ in their behaviour; for example, some may be faster than the others but at the expense of greater risk. We consider and study a distribution of optimal policies. We design a curiosity-augmented Metropolis algorithm (CAMEO), such that we can sample optimal policies, and such that these policies effectively adopt diverse behaviour…

Behaviour-Diverse Automatic Penetration Testing: A Curiosity-Driven Multi-Objective Deep Reinforcement Learning Approach

Penetration Testing plays a critical role in evaluating the security of a target network by emulating real active adversaries. Deep Reinforcement Learning (RL) is seen as a promising solution to automating the process of penetration tests by reducing human effort and improving reliability. Existing RL solutions focus on finding a specific attack path to impact the target hosts. However, in reality, a diverse range of attack variations are needed to provide comprehensive assessments of the target network's security level. Hence, the attack agents must consider multiple objectives when penetrati…

信息内容探索

Information Content Exploration

针对稀疏奖励环境下强化学习探索困难的问题，本文提出通过最大化轨迹信息内容的内在奖励方法，并在蒙特祖玛复仇等游戏中验证了其优于好奇心驱动学习和随机网络蒸馏，同时扩展至离散压缩潜在空间以提升样本效率。