Related papers: Meta-World Conditional Neural Processes
We introduce Unsupervised Meta-Testing with Conditional Neural Processes (UMCNP), a novel hybrid few-shot meta-reinforcement learning (meta-RL) method that uniquely combines, yet distinctly separates, parameterized policy gradient-based…
Conditional Neural Processes (CNP; Garnelo et al., 2018) are an attractive family of meta-learning models which produce well-calibrated predictions, enable fast inference at test time, and are trainable via a simple maximum likelihood…
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…
Trajectory planners of autonomous vehicles usually rely on physical models to predict the vehicle behavior. However, despite their suitability, physical models have some shortcomings. On the one hand, simple models suffer from larger model…
We present the Multi-Agent Transformer World Model (MATWM), a novel transformer-based world model designed for multi-agent reinforcement learning in both vector- and image-based environments. MATWM combines a decentralized imagination…
The capability of imagining internally with a mental model of the world is vitally important for human cognition. If a machine intelligent agent can learn a world model to create a "dream" environment, it can then internally ask what-if…
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the…
When building a world model, a common assumption is that the environment has a single, unchanging underlying causal rule, like applying Newton's laws to every situation. In reality, what appears as a drifting causal mechanism is often the…
Humans leverage rich internal models of the world to reason about the future, imagine counterfactuals, and adapt flexibly to new situations. In Reinforcement Learning (RL), world models aim to capture how the environment evolves in response…
Neural processes (NPs) are a powerful family of meta-learning models that seek to approximate the posterior predictive map of the ground-truth stochastic process from which each dataset in a meta-dataset is sampled. There are many cases in…
Few-shot natural language processing (NLP) refers to NLP tasks that are accompanied with merely a handful of labeled examples. This is a real-world challenge that an AI system must learn to handle. Usually we rely on collecting more…
Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…
Conditional Neural Processes~(CNPs) bridge neural networks with probabilistic inference to approximate functions of Stochastic Processes under meta-learning settings. Given a batch of non-{\it i.i.d} function instantiations, CNPs are…
Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…
The capacity of an embodied agent to understand, predict, and interact with its environment is fundamentally contingent on an internal world model. This paper introduces a novel framework for investigating the formation and adaptation of…
Machine learning (ML)-based weather models have recently undergone rapid improvements. These models are typically trained on gridded reanalysis data from numerical data assimilation systems. However, reanalysis data comes with limitations,…
Neural Processes (NPs) are meta-learning models that learn to map sets of observations to approximations of the corresponding posterior predictive distributions. By accommodating variable-sized, unstructured collections of observations and…
A longstanding goal of artificial general intelligence is highly capable generalists that can learn from diverse experiences and generalize to unseen tasks. The language and vision communities have seen remarkable progress toward this trend…
Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as in…
In this paper, we propose World Model Policy Gradient (WMPG), an approach to reduce the variance of policy gradient estimates using learned world models (WM's). In WMPG, a WM is trained online and used to imagine trajectories. The imagined…