Related papers: Dynamics Generalisation in Reinforcement Learning …
Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…
Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key…
A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…
Data driven approaches for decision making applied to automated driving require appropriate generalization strategies, to ensure applicability to the world's variability. Current approaches either do not generalize well beyond the training…
In this paper, we confront the problem of applying reinforcement learning to agents that perceive the environment through many sensors and that can perform parallel actions using many actuators as is the case in complex autonomous robots.…
The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…
Biological vision systems make adaptive use of context to recognize objects in new settings with novel contexts as well as occluded or blurry objects in familiar settings. In this paper, we investigate how vision models adaptively use…
Learning policies which are robust to changes in the environment are critical for real world deployment of Reinforcement Learning agents. They are also necessary for achieving good generalization across environment shifts. We focus on…
Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…
Video generative models demonstrate great promise in robotics by serving as visual planners or as policy supervisors. When pretrained on internet-scale data, such video models intimately understand alignment with natural language, and can…
A significant challenge in developing AI that can generalize well is designing agents that learn about their world without being told what to learn, and apply that learning to challenges with sparse rewards. Moreover, most traditional…
General intelligence requires quick adaption across tasks. While existing reinforcement learning (RL) methods have made progress in generalization, they typically assume only distribution changes between source and target domains. In this…
In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…
Making the right decision in traffic is a challenging task that is highly dependent on individual preferences as well as the surrounding environment. Therefore it is hard to model solely based on expert knowledge. In this work we use Deep…
Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learning algorithms that rely on incremental value updates. Rapid…
A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires…
In this paper, we study a transfer reinforcement learning problem where the state transitions and rewards are affected by the environmental context. Specifically, we consider a demonstrator agent that has access to a context-aware policy…
Transformer models can use two fundamentally different kinds of information: information stored in weights during training, and information provided ``in-context'' at inference time. In this work, we show that transformers exhibit different…
Adapting to the changes in transition dynamics is essential in robotic applications. By learning a conditional policy with a compact context, context-aware meta-reinforcement learning provides a flexible way to adjust behavior according to…
Deep Reinforcement Learning (DRL) agents frequently face challenges in adapting to tasks outside their training distribution, including issues with over-fitting, catastrophic forgetting and sample inefficiency. Although the application of…