相关论文: Learning Local Forward Models on Unforgiving Games

Reinforcement Learning is divided in two main paradigms: model-free and model-based. Each of these two paradigms has strengths and limitations, and has been successfully applied to real world domains that are appropriate to its…

This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple universal perturbation can fool a series of state-of-the-art…

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Recent deep learning models such as ChatGPT utilizing the back-propagation algorithm have exhibited remarkable performance. However, the disparity between the biological brain processes and the back-propagation algorithm has been noted. The…

Despite the continuous research and evolution of language models, they sometimes underperform previous versions. Existing approaches to overcome these challenges are resource-intensive, highlighting the need for alternatives that enable…

How do language models learn to make predictions during pre-training? To study this, we extract learning curves from five autoregressive English language model pre-training runs, for 1M unseen tokens in context. We observe that the language…

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

The concept of a recently proposed Forward-Forward learning algorithm for fully connected artificial neural networks is applied to a single multi output perceptron for classification. The parameters of the system are trained with respect to…

Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors,…

Precise load forecasting in buildings could increase the bill savings potential and facilitate optimized strategies for power generation planning. With the rapid evolution of computer science, data-driven techniques, in particular the Deep…

State-of-the-art backpropagation-free learning methods employ local error feedback to direct iterative optimisation via gradient descent. Here, we examine the more restrictive setting where retrograde communication from neuronal outputs is…

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbolic planners for solving complex decision making tasks. In this work, we demonstrate how to train…

Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent. In particular, it could help agents avoid potentially catastrophic exploratory actions, which would otherwise have to be…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Despite their impressive performance, many…

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most…

Performative prediction is a framework that captures distribution shifts that occur during the training of machine learning models due to their deployment. As the trained model is used, data generation causes the model to evolve, leading to…

Although recent model-free reinforcement learning algorithms have been shown to be capable of mastering complicated decision-making tasks, the sample complexity of these methods has remained a hurdle to utilizing them in many real-world…

Methods for learning latent user representations from historical behavior logs have gained traction for recommendation tasks in e-commerce, content streaming, and other settings. However, this area still remains relatively underexplored in…