Related papers: Powderworld: A Platform for Understanding Generali…

Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using large language model-based agent systems, and it is important for building agents that can…

Recent advances in deep learning have allowed Artificial Intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic or cognitive tasks. There is a growing need, however, for novel, brain-inspired…

Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically observe that an agent trained on many variations (a…

Achieving generalizable embodied policies remains a key challenge. Traditional policy learning paradigms, including both Imitation Learning (IL) and Reinforcement Learning (RL), struggle to cultivate generalizability across diverse…

An open problem in artificial intelligence is how to learn and represent knowledge that is sufficient for a general agent that needs to solve multiple tasks in a given world. In this work we propose world value functions (WVFs), which are a…

Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives…

The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this singular physical existence into a multiverse of games, each governed by entirely…

Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the…

Deep reinforcement learning (RL) agents trained in a limited set of environments tend to suffer overfitting and fail to generalize to unseen testing environments. To improve their generalizability, data augmentation approaches (e.g. cutout…

LLM-based agents have seen promising advances, yet they are still limited in "hard-exploration" tasks requiring learning new knowledge through exploration. We present GLoW, a novel approach leveraging dual-scale world models, maintaining a…

Physical intelligence holds immense promise for advancing embodied intelligence, enabling robots to acquire complex behaviors from demonstrations. However, achieving generalization and transfer across diverse robotic platforms and…

Training deep learning models takes an extremely long execution time and consumes large amounts of computing resources. At the same time, recent research proposed systems and compilers that are expected to decrease deep learning models…

To achieve general artificial intelligence, reinforcement learning (RL) agents should learn not only to optimize returns for one specific task but also to constantly build more complex skills and scaffold their knowledge about the world,…

The reliable deployment of deep reinforcement learning in real-world settings requires the ability to generalize across a variety of conditions, including both in-distribution scenarios seen during training as well as novel…

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

Reinforcement learning has recently shown promise in improving retrieval-augmented generation (RAG). Despite these advances, its effectiveness in multi-hop question answering (QA) remains limited by two fundamental limitations: (i) global…

Reinforcement learning (rl) is a popular paradigm for sequential decision making problems. The past decade's advances in rl have led to breakthroughs in many challenging domains such as video games, board games, robotics, and chip design.…

Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically. Motivated by the need to make games replayable, as well as to reduce…

The possibilities of robot control have multiplied across various domains through the application of deep reinforcement learning. To overcome safety and sampling efficiency issues, deep reinforcement learning models can be trained in a…