7.1k citations · 9.2k across the 24 of their papers we have counts for
25 papers
CocoaBench: Evaluating Unified Digital Agents in the Wild
CocoaBench Team, Shibo Hao, Zhining Zhang +29
LLM agents now perform strongly in software engineering, deep research, GUI automation, and various other applications, while recent agent scaffolds and models are increasingly int…
On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers
Miroslav Štrupl, Oleg Szehr, Francesco Faccio +3
This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Tran…
Bayesian Flow Networks
Alex Graves, Rupesh Kumar Srivastava, Timothy Atkinson +1
This paper introduces Bayesian Flow Networks (BFNs), a new class of generative model in which the parameters of a set of independent distributions are modified with Bayesian infere…
Universal Smoothed Score Functions for Generative Modeling
Saeed Saremi, Rupesh Kumar Srivastava, Francis Bach
We consider the problem of generative modeling based on smoothing an unknown density of interest in using factorial kernels with independent Gaussian channels wi…
EvoTorch: Scalable Evolutionary Computation in Python
Nihat Engin Toklu, Timothy Atkinson, Vojtěch Micka +2
Evolutionary computation is an important component within various fields such as artificial intelligence research, reinforcement learning, robotics, industrial automation and/or op…
Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets
Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley +2
Upside-Down Reinforcement Learning (UDRL) is an approach for solving RL problems that does not require value functions and uses only supervised learning, where the targets for give…
All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL
Kai Arulkumaran, Dylan R. Ashley, Jürgen Schmidhuber +1
Upside down reinforcement learning (UDRL) flips the conventional use of the return in the objective function in RL upside down, by taking returns as input and predicting actions. U…
Learning Relative Return Policies With Upside-Down Reinforcement Learning
Dylan R. Ashley, Kai Arulkumaran, Jürgen Schmidhuber +1
Lately, there has been a resurgence of interest in using supervised learning to solve reinforcement learning problems. Recent work in this area has largely focused on learning comm…
Multimeasurement Generative Models
Saeed Saremi, Rupesh Kumar Srivastava
We formally map the problem of sampling from an unknown distribution with a density in to the problem of learning and sampling a smoother density in $\mathbb{R}^{Md}…
Reward-Weighted Regression Converges to a Global Optimum
Miroslav Štrupl, Francesco Faccio, Dylan R. Ashley +2
Reward-Weighted Regression (RWR) belongs to a family of widely known iterative Reinforcement Learning algorithms based on the Expectation-Maximization framework. In this family, le…
ClipUp: A Simple and Powerful Optimizer for Distribution-based Policy Evolution
Nihat Engin Toklu, Paweł Liskowski, Rupesh Kumar Srivastava
Distribution-based search algorithms are an effective approach for evolutionary reinforcement learning of neural network controllers. In these algorithms, gradients of the total re…
Provable Robust Classification via Learned Smoothed Densities
Saeed Saremi, Rupesh Srivastava
Smoothing classifiers and probability density functions with Gaussian kernels appear unrelated, but in this work, they are unified for the problem of robust classification. The key…
Training Agents using Upside-Down Reinforcement Learning
Rupesh Kumar Srivastava, Pranav Shyam, Filipe Mutz +2
We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use rewar…
Artificial Intelligence for Prosthetics - challenge solutions
Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty +47
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a giv…
ContextVP: Fully Context-Aware Video Prediction
Wonmin Byeon, Qin Wang, Rupesh Kumar Srivastava +1
Video prediction models based on convolutional networks, recurrent networks, and their combinations often result in blurry predictions. We identify an important contributing factor…
Highway and Residual Networks learn Unrolled Iterative Estimation
Klaus Greff, Rupesh K. Srivastava, Jürgen Schmidhuber
The past year saw the introduction of new architectures such as Highway networks and Residual networks which, for the first time, enabled the training of feedforward networks with…
Recurrent Highway Networks
Julian Georg Zilly, Rupesh Kumar Srivastava, Jan Koutník +1
Many sequential processing tasks require complex nonlinear transition functions from one step to the next. However, recurrent neural networks with 'deep' transition functions remai…
Binding via Reconstruction Clustering
Klaus Greff, Rupesh Kumar Srivastava, Jürgen Schmidhuber
Disentangled distributed representations of data are desirable for machine learning, since they are more expressive and can generalize from fewer examples. However, for complex dat…
Training Very Deep Networks
Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber
Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and traini…
Highway Networks
Rupesh Kumar Srivastava, Klaus Greff, Jürgen Schmidhuber
There is plenty of theoretical and empirical evidence that depth of neural networks is a crucial ingredient for their success. However, network training becomes more difficult with…
Joint Learning of Distributed Representations for Images and Texts
Xiaodong He, Rupesh Srivastava, Jianfeng Gao +1
This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maxi…
LSTM: A Search Space Odyssey
Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník +2
Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks hav…
From Captions to Visual Concepts and Back
Hao Fang, Saurabh Gupta, Forrest Iandola +9
This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dat…
Understanding Locally Competitive Networks
Rupesh Kumar Srivastava, Jonathan Masci, Faustino Gomez +1
Recently proposed neural network activation functions such as rectified linear, maxout, and local winner-take-all have allowed for faster and more effective training of deep neural…