106 citations · 126 across the 9 of their papers we have counts for
10 papers
Pretrained Features as Teachers, Not States: Compact Latent World Models for Visual Planning
Yanbo Wang, Nan Lin, Wendelin Böhmer +1
A key design choice in visual world models is what information the latent state is encouraged to preserve. Models that learn a latent space with only a latent-prediction objective…
Twice Sequential Monte Carlo for Tree Search
Yaniv Oren, Joery A. de Vries, Pascal R. van der Vaart +2
Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alt…
Improving Robustness of AlphaZero Algorithms to Test-Time Environment Changes
Isidoro Tamassia, Wendelin Böhmer
The AlphaZero framework provides a standard way of combining Monte Carlo planning with prior knowledge provided by a previously trained policy-value neural network. AlphaZero usual…
Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control
Laurens Engwegen, Max Weltevrede, Caroline Horsch +2
A universal controller for any robot morphology would greatly improve computational and data efficiency. Steps have been made towards such multi-robot control by utilizing contextu…
Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs
Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan +1
In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones. Re…
To the Max: Reinventing Reward in Reinforcement Learning
Grigorii Veviurko, Wendelin Böhmer, Mathijs de Weerdt
In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stu…
You Shall Pass: Dealing with the Zero-Gradient Problem in Predict and Optimize for Convex Optimization
Grigorii Veviurko, Wendelin Böhmer, Mathijs de Weerdt
Predict and optimize is an increasingly popular decision-making paradigm that employs machine learning to predict unknown parameters of optimization problems. Instead of minimizing…
Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
Shariq Iqbal, Christian A. Schroeder de Witt, Bei Peng +3
Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge amo…
FACMAC: Factored Multi-Agent Centralised Policy Gradients
Bei Peng, Tabish Rashid, Christian A. Schroeder de Witt +4
We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces…
Robot Navigation using Reinforcement Learning and Slow Feature Analysis
Wendelin Böhmer
The application of reinforcement learning algorithms onto real life problems always bears the challenge of filtering the environmental state out of raw sensor readings. While most…