50 citations · 163 across the 21 of their papers we have counts for
21 papers
Generalization in offline RL: The structure is more important than the amount of pessimism
Max Weltevrede, Matthijs T. J. Spaan, Wendelin Böhmer
While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization…
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
Thomas Evers, Cristian Meo, Wendelin Bohmer +2
We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is…
Particle Monte Carlo Tree Search
Yaniv Oren, Viliam Vadocz, Joery A. de Vries +3
Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement and action selection in Reinforcement Learning. Due to its sequential and deterministic nature, prin…
Generalisation to unseen topologies: Towards control of biological neural network activity
Laurens Engwegen, Daan Brinks, Wendelin Böhmer
Novel imaging and neurostimulation techniques open doors for advancements in closed-loop control of activity in biological neural networks. This would allow for applications in the…
Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning
Max Weltevrede, Felix Kaubek, Matthijs T. J. Spaan +1
One of the remaining challenges in reinforcement learning is to develop agents that can generalise to novel scenarios they might encounter once deployed. This challenge is often fr…
Lights out: training RL agents robust to temporary blindness
N. Ordonez, M. Tromp, P. M. Julbe +1
Agents trained with DQN rely on an observation at each timestep to decide what action to take next. However, in real world applications observations can change or be missing entire…
Multi-Robot Local Motion Planning Using Dynamic Optimization Fabrics
Saray Bakker, Luzia Knoedler, Max Spahn +2
In this paper, we address the problem of real-time motion planning for multiple robotic manipulators that operate in close proximity. We build upon the concept of dynamic fabrics a…
Diverse Projection Ensembles for Distributional Reinforcement Learning
Moritz A. Zanger, Wendelin Böhmer, Matthijs T. J. Spaan
In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of th…
The Role of Diverse Replay for Generalisation in Reinforcement Learning
Max Weltevrede, Matthijs T. J. Spaan, Wendelin Böhmer
In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and t…
Active Classification of Moving Targets with Learned Control Policies
Álvaro Serra-Gómez, Eduardo Montijano, Wendelin Böhmer +1
In this paper, we consider the problem where a drone has to collect semantic information to classify multiple moving targets. In particular, we address the challenge of computing c…
UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
Tarun Gupta, Anuj Mahajan, Bei Peng +2
VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this ena…
Optimistic Exploration even with a Pessimistic Initialisation
Tabish Rashid, Bei Peng, Wendelin Böhmer +1
Optimistic initialisation is an effective strategy for efficient exploration in reinforcement learning (RL). In the tabular case, all provably efficient model-free algorithms rely…
Multi-agent Hierarchical Reinforcement Learning with Dynamic Termination
Dongge Han, Wendelin Boehmer, Michael Wooldridge +1
In a multi-agent system, an agent's optimal policy will typically depend on the policies chosen by others. Therefore, a key issue in multi-agent systems research is that of predict…
Deep Coordination Graphs
Wendelin Böhmer, Vitaly Kurin, Shimon Whiteson
This paper introduces the deep coordination graph (DCG) for collaborative multi-agent reinforcement learning. DCG strikes a flexible trade-off between representational capacity and…
Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
Wendelin Böhmer, Tabish Rashid, Shimon Whiteson
This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple c…
Deep Residual Reinforcement Learning
Shangtong Zhang, Wendelin Boehmer, Shimon Whiteson
We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algor…
Multitask Soft Option Learning
Maximilian Igl, Andrew Gambardella, Jinke He +4
We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational…
Generalized Off-Policy Actor-Critic
Shangtong Zhang, Wendelin Boehmer, Shimon Whiteson
We propose a new objective, the counterfactual objective, unifying existing objectives for off-policy policy gradient algorithms in the continuing reinforcement learning (RL) setti…
Multi-Agent Common Knowledge Reinforcement Learning
Christian A. Schroeder de Witt, Jakob N. Foerster, Gregory Farquhar +3
Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents' ability to coordinate their behaviour. In this paper, we show…
Non-Deterministic Policy Improvement Stabilizes Approximated Reinforcement Learning
Wendelin Böhmer, Rong Guo, Klaus Obermayer
This paper investigates a type of instability that is linked to the greedy policy improvement in approximated reinforcement learning. We show empirically that non-deterministic pol…
Regression with Linear Factored Functions
Wendelin Böhmer, Klaus Obermayer
Many applications that use empirically estimated functions face a curse of dimensionality, because the integrals over most function classes must be approximated by sampling. This p…