62 citations · 126 across the 27 of their papers we have counts for
29 papers
Continual Graph Multi-Agent Reinforcement Learning
Tommaso Marzi, Ahmed Hendawy, Jan Peters +3
In Continual Multi-Agent Reinforcement Learning (CMARL), agents learn cooperative policies across sequences of tasks, aiming to adapt effectively to new tasks while preserving the…
Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement
Mahdi Kallel, Johannes Tölle, Ahmed Hendawy +1
Standard supervised classification trains models to imitate the exact labels provided by a perfect oracle. This imitation happens in a single pass, restricting the model to a fixed…
Gradient Iterated Temporal-Difference Learning
Théo Vincent, Kevin Gerhardt, Yogesh Tripathi +5
Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this paradigm implement a semi-gradient update…
Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning
Ahmed Hendawy, Henrik Metternich, Théo Vincent +3
The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target network remains a compromise soluti…
-Level Policy Gradients for Multi-Agent Reinforcement Learning
Aryaman Reddi, Gabriele Tiboni, Jan Peters +1
Actor-critic algorithms for deep multi-agent reinforcement learning (MARL) typically employ a policy update that responds to the current strategies of other agents. While being str…
Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning
Théo Vincent, Yogesh Tripathi, Tim Faust +5
The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, targ…
Eau De -Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning
Théo Vincent, Tim Faust, Yogesh Tripathi +2
Recent works have successfully demonstrated that sparse deep reinforcement learning agents can be competitive against their dense counterparts. This opens up opportunities for rein…
Deterministic Exploration via Stationary Bellman Error Maximization
Sebastian Griesbach, Carlo D'Eramo
Exploration is a crucial and distinctive aspect of reinforcement learning (RL) that remains a fundamental open problem. Several methods have been proposed to tackle this challenge.…
Machine Learning with Physics Knowledge for Prediction: A Survey
Joe Watson, Chen Song, Oliver Weeger +12
This survey examines the broad suite of methods and models for combining machine learning with physics knowledge for prediction and forecast, with a focus on partial differential e…
Augmented Bayesian Policy Search
Mahdi Kallel, Debabrota Basu, Riad Akrour +1
Deterministic policies are often preferred over stochastic ones when implemented on physical systems. They can prevent erratic and harmful behaviors while being easier to implement…
Adaptive -Network: On-the-fly Target Selection for Deep Reinforcement Learning
Théo Vincent, Fabian Wahren, Jan Peters +2
Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand.…
Iterated -Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning
Théo Vincent, Daniel Palenicek, Boris Belousov +2
The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functio…
Sharing Knowledge in Multi-Task Deep Reinforcement Learning
Carlo D'Eramo, Davide Tateo, Andrea Bonarini +2
We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning. We leverage the assumption tha…
Parameterized Projected Bellman Operator
Théo Vincent, Alberto Maria Metelli, Boris Belousov +3
Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algor…
Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
Aryaman Reddi, Maximilian Tölle, Jan Peters +2
Robustness against adversarial attacks and distribution shifts is a long-standing goal of Reinforcement Learning (RL). To this end, Robust Adversarial Reinforcement Learning (RARL)…
Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
Ahmed Hendawy, Jan Peters, Carlo D'Eramo
Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems. To this end, sharing represe…
Domain Randomization via Entropy Maximization
Gabriele Tiboni, Pascal Klink, Jan Peters +3
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL). Nevertheless, DR heavily hi…
Monte-Carlo tree search with uncertainty propagation via optimal transport
Tuan Dam, Pascal Stenger, Lukas Schneider +3
This paper introduces a novel backup strategy for Monte-Carlo Tree Search (MCTS) designed for highly stochastic and partially observable Markov decision processes. We adopt a proba…
On the Benefit of Optimal Transport for Curriculum Reinforcement Learning
Pascal Klink, Carlo D'Eramo, Jan Peters +1
Curriculum reinforcement learning (CRL) allows solving complex tasks by generating a tailored sequence of learning tasks, starting from easy ones and subsequently increasing their…
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search
Tuan Dam, Carlo D'Eramo, Jan Peters +1
Monte-Carlo Tree Search (MCTS) is a class of methods for solving complex decision-making problems through the synergy of Monte-Carlo planning and Reinforcement Learning (RL). The h…
Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning
Julen Urain, Anqi Li, Puze Liu +2
Reactive motion generation problems are usually solved by computing actions as a sum of policies. However, these policies are independent of each other and thus, they can have conf…
Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning
Andrew S. Morgan, Daljeet Nandha, Georgia Chalvatzaki +3
Substantial advancements to model-based reinforcement learning algorithms have been impeded by the model-bias induced by the collected data, which generally hurts performance. Mean…
A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning
Pascal Klink, Hany Abdulsamad, Boris Belousov +3
Across machine learning, the use of curricula has shown strong empirical potential to improve learning from data by avoiding local optima of training objectives. For reinforcement…
Convex Regularization in Monte-Carlo Tree Search
Tuan Dam, Carlo D'Eramo, Jan Peters +1
Monte-Carlo planning and Reinforcement Learning (RL) are essential to sequential decision making. The recent AlphaGo and AlphaZero algorithms have shown how to successfully combine…