2.3k citations · 2.4k across the 19 of their papers we have counts for
22 papers
Gradient-Based Program Synthesis with Neurally Interpreted Languages
Matthew V. Macfarlane, Clément Bonnet, Herke van Hoof +1
A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional generalisation and data efficiency…
The Unfairness of Multifactorial Bias in Recommendation
Masoud Mansoury, Jin Huang, Mykola Pechenizkiy +2
Popularity bias and positivity bias are two prominent sources of bias in recommender systems. Both arise from input data, propagate through recommendation models, and lead to unfai…
Data Augmentation for Instruction Following Policies via Trajectory Segmentation
Niklas Höpner, Ilaria Tiddi, Herke van Hoof
The scalability of instructable agents in robotics or gaming is often hindered by limited data that pairs instructions with agent trajectories. However, large datasets of unannotat…
Bridge the Inference Gaps of Neural Processes via Expectation Maximization
Qi Wang, Marco Federici, Herke van Hoof
The neural process (NP) is a family of computationally efficient models for learning distributions over functions. However, it suffers from under-fitting and shows suboptimal perfo…
Calculus on MDPs: Potential Shaping as a Gradient
Erik Jenner, Herke van Hoof, Adam Gleave
In reinforcement learning, different reward functions can be equivalent in terms of the optimal policies they induce. A particularly well-known and important example is potential s…
Neural Topological Ordering for Computation Graphs
Mukul Gagrani, Corrado Rainone, Yang Yang +7
Recent works on machine learning for combinatorial optimization have shown that learning based approaches can outperform heuristic methods in terms of speed and performance. In thi…
Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine
Charul Giri, Ole-Christoffer Granmo, Herke van Hoof +1
Hex is a turn-based two-player connection game with a high branching factor, making the game arbitrarily complex with increasing board sizes. As such, top-performing algorithms for…
Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment
Tessa van der Heiden, Herke van Hoof, Efstratios Gavves +1
We consider multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents can be brittle because they can overfit their training partn…
Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation
Alexander Long, Alan Blair, Herke van Hoof
We present Nonparametric Approximation of Inter-Trace returns (NAIT), a Reinforcement Learning algorithm for discrete action, pixel-based environments that is both highly sample an…
Multi-Agent MDP Homomorphic Networks
Elise van der Pol, Herke van Hoof, Frans A. Oliehoek +1
This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience betw…
A Survey of Exploration Methods in Reinforcement Learning
Susan Amin, Maziar Gomrokchi, Harsh Satija +2
Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinfor…
Combining Reward Information from Multiple Sources
Dmitrii Krasheninnikov, Rohin Shah, Herke van Hoof
Given two sources of evidence about a latent variable, one can combine the information from both by multiplying the likelihoods of each piece of evidence. However, when one or both…
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models
Qi Wang, Herke van Hoof
Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real…
Robust Multi-Agent Reinforcement Learning with Social Empowerment for Coordination and Communication
T. van der Heiden, C. Salge, E. Gavves +1
We consider the problem of robust multi-agent reinforcement learning (MARL) for cooperative communication and coordination tasks. MARL agents, mainly those trained in a centralized…
Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables
Qi Wang, Herke van Hoof
Neural processes (NPs) constitute a family of variational approximate models for stochastic processes with promising properties in computational efficiency and uncertainty quantifi…
An Autonomous Free Airspace En-route Controller using Deep Reinforcement Learning Techniques
Joris Mollinga, Herke van Hoof
Air traffic control is becoming a more and more complex task due to the increasing number of aircraft. Current air traffic control methods are not suitable for managing this increa…
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
Elise van der Pol, Daniel E. Worrall, Herke van Hoof +2
This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint stat…
Reinforcement Learning with Non-uniform State Representations for Adaptive Search
Sandeep Manjanna, Herke van Hoof, Gregory Dudek
Efficient spatial exploration is a key aspect of search and rescue. In this paper, we present a search algorithm that generates efficient trajectories that optimize the rate at whi…
Deep Generative Modeling of LiDAR Data
Lucas Caccia, Herke van Hoof, Aaron Courville +1
Building models capable of generating structured output is a key challenge for AI and robotics. While generative models have been explored on many types of data, little work has be…
BanditSum: Extractive Summarization as a Contextual Bandit
Yue Dong, Yikang Shen, Eric Crawford +2
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call…
Addressing Function Approximation Error in Actor-Critic Methods
Scott Fujimoto, Herke van Hoof, David Meger
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We…
Policy Search with High-Dimensional Context Variables
Voot Tangkaratt, Herke van Hoof, Simone Parisi +3
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning…