Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this direction inspired by human mental simulation of motor behavior. We propose a lea…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “experience imagination”
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state …
This paper improves robot grasping by integrating meta-control and latent-space imagination.
problem Dual-system approaches fail to consider the reliability of the learned model when making multiple-step predictions.
method A meta-controller arbitrates between model-based and model-free decisions based on local reliability, encouraging actions that improve the model and generating imagined experiences for additional training.
result Our approach learns near-optimal grasping policies in dense- and sparse-reward environments, outperforming baseline and state-of-the-art methods.
Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a plan. Here we introduce the "Imagination-based Planner", the first m…
Unified model improves object-centric world modeling with new abilities.
problem Integration of recent advances and temporal imagination abilities.
method Generative Structured World Models (G-SWM) framework.
result G-SWM achieves best or comparable performance in temporal generation.
This document consists of the collection of handouts for a two-week summer workshop entitled 'Geometry and the Imagination', led by John Conway, Peter Doyle, Jane Gilman and Bill Thurston at the Geometry Center in Minneapolis, June 17-28, 1991. The workshop was based on a course `Geometry and the Imagination' which we …
Reinforcement learning has seen great advancements in the past five years. The successful introduction of deep learning in place of more traditional methods allowed reinforcement learning to scale to very complex domains achieving super-human performance in environments like the game of Go or numerous video games. Desp…
Novel deep learning architecture decodes imagined speech from EEG.
problem Insufficient training samples for deep learning in decoding imagined speech.
method Employed a novel deep learning architecture with CSP for feature selection, DWT for feature extraction, and majority voting for classification.
result Achieved accuracies comparable to state-of-the-art results.
Dreamer 4 learns Minecraft tasks from videos alone.
problem Accurately predicting object interactions in complex environments.
method Reinforcement learning inside a fast, accurate world model.
result Dreamer 4 outperforms previous models in Minecraft, learning from only offline data.
It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic concepts visually grounded imagination. In this paper, we show how we can modify variational auto-encoders to perform this task. Our method use…
New approach to counterfactual reasoning avoids demographic interventions.
problem Limitations of traditional counterfactual reasoning in AI systems.
method Backtracking counterfactual approach instead of interventional.
result Allows addressing social concerns without demographic interventions.
WMPG reduces policy gradient variance using world models.
problem Reducing variance in policy gradient estimates.
method Trains a world model online to estimate policy gradients and uses imagined trajectories as a baseline.
result WMPG achieves better sample efficiency compared to AC and MAC.
Constellation learns group-level visual relationships for abstract reasoning.
problem Learning configurational properties of entire groups of objects.
method Introduces Constellation, a network that learns relational abstractions over static visual scenes.
result Offers a basis for abstract relational reasoning and sensory imagination.
While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural networks to map joint representations of observations and instructions directly to act…
Improved fMRI activation detection for single-subject studies.
problem Challenges in detecting activation in low-signal fMRI studies.
method Model-based approach using MixfMRI R package.
result Reliable activation detection in single-subject fMRI studies.
New model explains how concepts grow based on experience.
problem Existing models assume fixed representation; new model allows for growth.
method Geometric framework with MDL criterion for basis extension.
result Conceptual growth is selective and conservative, exposing or amplifying residual error.
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to inter…
Deep imagination optimizes decision-making in large trees with limited resources.
problem Optimal planning in large decision trees with limited resources and time.
method Analytical solutions and numerical analysis of sampling capacity allocation.
result Optimal policy is to allocate few samples per level for deep exploration, favoring depth over breadth.
Speech-related Brain Computer Interface (BCI) technologies provide effective vocal communication strategies for controlling devices through speech commands interpreted from brain signals. In order to infer imagined speech from active thoughts, we propose a novel hierarchical deep learning BCI system for subject-indepen…
A new method for robot manipulation tasks using imagined object goals.
problem Learning robot manipulation in sparse reward environments.
method Train objects to reach target positions, then use predictions to create a curriculum of tasks.
result Higher success rates in challenging learning scenarios compared to alternatives.
Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complexity. Such methods hold the promise of incorporating imagined data coupled with a notion of model uncertainty to accelerate the learning of c…
New Dreamer model tackles object vanishing in robot learning.
problem Object vanishing in Dreamer's latent state-space models.
method Decoder-free approach with InfoMax objective and data augmentation.
result Dreaming achieves best scores on 5 difficult robotics tasks.
We propose a mixed deep neural network strategy, incorporating parallel combination of Convolutional (CNN) and Recurrent Neural Networks (RNN), cascaded with deep autoencoders and fully connected layers towards automatic identification of imagined speech from EEG. Instead of utilizing raw EEG channel data, we compute t…
In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …
Infinitary braid groupsmath.GT
An infinitary version of braid groups has been considered as a direct limit of n-braid groups. However, we can imagine more complicated braids with infinitely many strings. We invetisgate basic properties especially when the number of strings is countable.
This article focuses on the work of O. Chanel and G. Chichilnisky (2013) on the flaws of expected utility theory while assessing the value of life. Expected utility is a fundamental tool in decision theory. However, it does not fit with the experimental results when it comes to catastrophic outcomes ---see, for example…
Together with the Moebius strip, the Klein bottle is one of the intriguing objects in the universe of geometry, sometimes appearing in non-mathematical contexts too. Until now, several parametrizations of it as a surface immersed in ordinary three-space have been found, some of which are very elegant and lead to nice a…
The use of synthetic data generated by Generative Adversarial Networks (GANs) has become quite a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to get more synthetic data that can be used to train downstream classifiers, it is not clear that they re…
UWM-JEPA predicts future scenarios in belief space, improving accuracy in partially observed environments.
problem Predicting future scenarios in partially observed environments with uncertainty.
method Introduces UWM-JEPA, a JEPA world model with a density-matrix latent and learned unitary predictor.
result UWM-JEPA achieves 0.77 accuracy on a hidden-velocity indicator task, outperforming LSTM-JEPA.
In this paper we explore the richness of information captured by the latent space of a vision-based generative model. The model combines unsupervised generative learning with a task-based performance predictor to learn and to exploit task-relevant object affordances given visual observations from a reaching task, invol…
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills must handle raw sensory input such as images. In this paper, we propose an algo…
Model predicts multi-agent trajectories using a differentiable simulator.
problem Predicting future positions of multiple interacting agents.
method Conditional recurrent variational neural networks (CVRNNs) with a kinematic bicycle model.
result Achieves state-of-the-art results on INTERACTION dataset.
Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge. We propose a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoencoder with Shared Emb…
Riemannian metric learning improves data representation across various fields.
problem Traditional distance metrics fail to capture intrinsic data geometry.
method Leverages differential geometry to model data on Riemannian manifolds.
result Demonstrates remarkable success in diverse domains.
Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the inpu…
REFIL learns from imagined sub-group interactions to improve multi-agent reinforcement learning.
problem Learning efficiency in multi-agent reinforcement learning settings.
method Randomized Entity-wise Factorization (REFIL) approach.
result REFIL outperforms all strong baselines in challenging multi-task StarCraft settings.
Models necessarily capture only parts of a reality. Prediction models aim at capturing a future reality. In this paper we address the question of how the future is constructed (or: imagined) in an investment context where market participants form expectations on the returns of a risky investment. We observe that the pa…
Consider a set of latent factors whose observable effect of activation is caught on a measure space that appears as a grid of bits tacking value in . This paper intend to deliver a theoretical and practical answer to the question: Given that we have access to a perfect indicator of the activation of latent f…
The problem of replicating the flexibility of human common-sense reasoning has captured the imagination of computer scientists since the early days of Alan Turing's foundational work on computation and the philosophy of artificial intelligence. In the intervening years, the idea of cognition as computation has emerged …
One of the open challenges in designing robots that operate successfully in the unpredictable human environment is how to make them able to predict what actions they can perform on objects, and what their effects will be, i.e., the ability to perceive object affordances. Since modeling all the possible world interactio…
Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based approaches lead to `compounding errors' when the model is unrolled step by step. Essentia…
Just as semantic hashing can accelerate information retrieval, binary valued embeddings can significantly reduce latency in the retrieval of graphical data. We introduce a simple but effective model for learning such binary vectors for nodes in a graph. By imagining the embeddings as independent coin flips of varying b…
GEGL uses genetic experts to improve deep learning for molecular design.
problem Designing molecules with desired properties using deep learning.
method Genetic expert-guided learning (GEGL) framework for training DNN.
result Significantly improves molecular design, achieving high scores on benchmarks.
Chess engines Stockfish and LCZero differ in their approach to solving endgame puzzles.
problem Comparing machine and human chess problem-solving abilities.
method Used Plaskett's Puzzle to compare Stockfish and LCZero's performance.
result Stockfish outperforms LCZero on the puzzle.
We demonstrate a conditional autoregressive pipeline for efficient music recomposition, based on methods presented in van den Oord et al.(2017). Recomposition (Casal & Casey, 2010) focuses on reworking existing musical pieces, adhering to structure at a high level while also re-imagining other aspects of the work. This…
As a promising area in artificial intelligence, a new learning paradigm, called Small Sample Learning (SSL), has been attracting prominent research attention in the recent years. In this paper, we aim to present a survey to comprehensively introduce the current techniques proposed on this topic. Specifically, current S…
PlanGAN uses GANs to plan efficient trajectories for multi-goal tasks in sparse reward environments.
problem Learning with sparse rewards in multi-goal environments.
method PlanGAN combines GANs to generate trajectories leading to specified goals, then combines these into a planning algorithm.
result PlanGAN achieves comparable performance to model-free RL but is 4-8 times more sample efficient.
Chirped sinosoids and interferometric phase plots are functions that are not periodic, but are the composition of a smooth function and a periodic function. These functions functions factor into a pair of maps: from their domain to a circle, and from a circle to their codomain. One can easily imagine replacing the circ…