Novelty Detection in Reinforcement Learning with World Models
Reinforcement learning (RL) using world models has found significant recent successes. However, when a sudden change to world mechanics or properties occurs then agent performance and reliability can dramatically decline. We refer to the sudden change in visual properties or state transitions as novelties. Implementing novelty detection within generated world model frameworks is a crucial task for protecting the agent when deployed. In this paper, we propose straightforward bounding approaches to incorporate novelty detection into world model RL agents, by utilizing the misalignment of the world model's hallucinated states and the true observed states as an anomaly score. We provide effective approaches to detecting novelties in a distribution of transitions learned by an agent in a world model. Finally, we show the advantage of our work in a novel environment compared to traditional machine learning novelty detection methods as well as currently accepted RL focused novelty detection algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingNovelty Detectionreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neuro-Symbolic World Models for Adapting to Open World Novelty
Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Mos…
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Detecting and Adapting to Novelty in Games
Open-world novelty occurs when the rules of an environment can change abruptly, such as when a game player encounters "house rules". To address open-world novelty, game playing agents must be able to detect when novelty …
Knowledge GraphsModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)The Difficulty of Novelty Detection in Open-World Physical Domains: An Application to Angry Birds
Detecting and responding to novel situations in open-world environments is a key capability of human cognition and is a persistent problem for AI systems. In an open-world, novelties can appear in many different forms an…
Novelty DetectionNovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds
In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty. However, visual novelty detection research often only evaluates on repurposed …
MinecraftNovelty DetectionKernel Null Space Methods for Novelty Detection
Detecting samples from previously unknown classes is a crucial task in object recognition, especially when dealing with real-world applications where the closed-world assumption does not hold. We present how to apply a n…
Density EstimationNovelty DetectionObject Recognition