Related papers: World Models
Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often…
The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive…
World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have…
Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where…
In the natural world, life has found innumerable ways to survive and often thrive. Between and even within species, each individual is in some manner unique, and this diversity lends adaptability and robustness to life. In this work, we aim…
We propose a set of precise criteria for saying a neural net learns and uses a "world model." The goal is to give an operational meaning to terms that are often used informally, in order to provide a common language for experimental…
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external…
Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models. We show that carefully designed generative models that learn and operate on compact state…
Offline meta-reinforcement learning seeks to learn policies that generalize across related tasks from fixed datasets. Context-based methods infer a task representation from transition histories, but learning effective task representations…
Despite the recent progress in deep learning and reinforcement learning, transfer and generalization of skills learned on specific tasks is very limited compared to human (or animal) intelligence. The lifelong, incremental building of…
Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for…
Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such…
World models represent a paradigm shift in generative AI, pursuing predictive understanding and controllable simulation of environments in a structured and generalizable way. We present World Machine, a generative world-modeling…
Planning with world models offers a powerful paradigm for robotic control. Conventional approaches train a model to predict future frames conditioned on current frames and actions, which can then be used for planning. However, the objective…
We introduce a generic, compositional and interpretable class of generative world models that supports open-ended learning agents. This is a sparse class of Bayesian networks capable of approximating a broad range of stochastic processes,…
Social dilemmas are situations where groups of individuals can benefit from mutual cooperation but conflicting interests impede them from doing so. This type of situations resembles many of humanity's most critical challenges, and…
Nowadays, model-free reinforcement learning algorithms have achieved remarkable performance on many decision making and control tasks, but high sample complexity and low sample efficiency still hinder the wide use of model-free…
Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and…
Some of the most important tasks take place in environments which lack cheap and perfect simulators, thus hampering the application of model-free reinforcement learning (RL). While model-based RL aims to learn a dynamics model, in a more…