相关论文: Goal Misgeneralization in Deep Reinforcement Learn…

The capacity to generalize beyond the range of training data is a pivotal challenge, often synonymous with a model's utility and robustness. This study investigates the comparative abilities of traditional machine learning (ML) models and…

Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. To understand how reward hacking arises, we construct four RL environments with misspecified…

Real-world sequential decision-making tasks often require balancing trade-offs between multiple conflicting objectives, making Multi-Objective Reinforcement Learning (MORL) an increasingly prominent field of research. Despite recent…

Deep reinforcement learning (DRL) is a very active research area. However, several technical and scientific issues require to be addressed, amongst which we can mention data inefficiency, exploration-exploitation trade-off, and multi-task…

We investigate the generalization boundaries of current Multimodal Large Language Models (MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks. We evaluate their zero-shot generalization across…

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Offline goal-conditioned RL (GCRL) offers a way to train general-purpose agents from fully offline datasets. In addition to being conservative within the dataset, the generalization ability to achieve unseen goals is another fundamental…

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of…

Building generalizable goal-conditioned agents from rich observations is a key to reinforcement learning (RL) solving real world problems. Traditionally in goal-conditioned RL, an agent is provided with the exact goal they intend to reach.…

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not…

Due to the realization that deep reinforcement learning algorithms trained on high-dimensional tasks can strongly overfit to their training environments, there have been several studies that investigated the generalization performance of…

When decisions are made at high frequency, traditional reinforcement learning (RL) methods struggle to accurately estimate action values. In turn, their performance is inconsistent and often poor. Whether the performance of distributional…

Supervised learning (SL) and reinforcement learning (RL) are both widely used to train general-purpose agents for complex tasks, yet their generalization capabilities and underlying mechanisms are not yet fully understood. In this paper, we…

Deep reinforcement learning (RL) has achieved outstanding results in recent years, which has led a dramatic increase in the number of methods and applications. Recent works are exploring learning beyond single-agent scenarios and…

We study the problem of predicting and controlling the future state distribution of an autonomous agent. This problem, which can be viewed as a reframing of goal-conditioned reinforcement learning (RL), is centered around learning a…

There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such…

This paper explores the mechanistic interpretability of reinforcement learning (RL) agents through an analysis of a neural network trained on procedural maze environments. By dissecting the network's inner workings, we identified…

As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and…

Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with…

Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online…