187 citations · 331 across the 16 of their papers we have counts for
16 papers
Coachable agents for interactive gameplay
Roberto Capobianco, Harm van Seijen, Nolan D. Bard +38
Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation m…
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
Mingde Zhao, Safa Alver, Harm van Seijen +3
Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situat…
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Riashat Islam, Manan Tomar, Alex Lamb +8
Learning to control an agent from data collected offline in a rich pixel-based visual observation space is vital for real-world applications of reinforcement learning (RL). A major…
Modular Lifelong Reinforcement Learning via Neural Composition
Jorge A. Mendez, Harm van Seijen, Eric Eaton
Humans commonly solve complex problems by decomposing them into easier subproblems and then combining the subproblem solutions. This type of compositional reasoning permits reuse o…
One-Shot Learning from a Demonstration with Hierarchical Latent Language
Nathaniel Weir, Xingdi Yuan, Marc-Alexandre Côté +5
Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration. They are able to describe unseen task-performing procedur…
Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
Sungryull Sohn, Sungtae Lee, Jongwook Choi +3
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent's trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal p…
The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
Harm van Seijen, Hadi Nekoei, Evan Racah +1
Deep model-based Reinforcement Learning (RL) has the potential to substantially improve the sample-efficiency of deep RL. While various challenges have long held it back, a number…
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Arash Tavakoli
In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to st…
Learning Invariances for Policy Generalization
Remi Tachet, Philip Bachman, Harm van Seijen
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unse…
Hybrid Reward Architecture for Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Joshua Romoff +3
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dime…
Multi-Advisor Reinforcement Learning
Romain Laroche, Mehdi Fatemi, Joshua Romoff +1
We consider tackling a single-agent RL problem by distributing it to learners. These learners, called advisors, endeavour to solve the problem from a different focus. Their adv…
Separation of Concerns in Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Joshua Romoff +1
In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantage…
Effective Multi-step Temporal-Difference Learning for Non-Linear Function Approximation
Harm van Seijen
Multi-step temporal-difference (TD) learning, where the update targets contain information from multiple time steps ahead, is one of the most popular forms of TD learning for linea…
True Online Temporal-Difference Learning
Harm van Seijen, A. Rupam Mahmood, Patrick M. Pilarski +2
The temporal-difference methods TD() and Sarsa() form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, an…
An Empirical Evaluation of True Online TD(λ)
Harm van Seijen, A. Rupam Mahmood, Patrick M. Pilarski +1
The true online TD(λ) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD(λ) algorithm, in temporal-difference learning…
Planning by Prioritized Sweeping with Small Backups
Harm van Seijen, Richard S. Sutton
Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the suc…