Related papers: Learning Local Forward Models on Unforgiving Games
Can a mere next-token predictor faithfully model human intelligence? We crystallize this emerging concern and correct popular misconceptions surrounding it, and advocate a simple multi-token objective. As a starting point, we argue that the…
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making,…
Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our…
In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is…
We aim to create a framework for transfer learning using latent factor models to learn the dependence structure between a larger source dataset and a target dataset. The methodology is motivated by our goal of building a risk-assessment…
With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…
When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…
Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…
Reinforcement learning has been successfully used to solve difficult tasks in complex unknown environments. However, these methods typically do not provide any safety guarantees during the learning process. This is particularly problematic,…
World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World models typically…
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized…
Modern applications of machine learning (ML) deal with increasingly heterogeneous datasets comprised of data collected from overlapping latent subpopulations. As a result, traditional models trained over large datasets may fail to recognize…
Self-supervised representation learning has seen remarkable progress in the last few years, with some of the recent methods being able to learn useful image representations without labels. These methods are trained using backpropagation,…
In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a…
Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically…
In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…
A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…
Estimating how often an ML model will fail at deployment scale is central to pre-deployment safety assessment, but a feasible evaluation set is rarely large enough to observe the failures that matter. Jones et al. (2025) address this by…
A World Model is a compressed spatial and temporal representation of a real world environment that allows one to train an agent or execute planning methods. However, world models are typically trained on observations from the real world…
Transfer learning is beneficial for survival analysis, especially when the target study has a limited number of events. However, existing transfer learning methods rely on the restrictive assumption that the target and source studies share…