382 citations · 666 across the 86 of their papers we have counts for
15 papers · 1 filter
Hybrid Search for Efficient Planning with Completeness Guarantees
Kalle Kujanpää, Joni Pajarinen, Alexander Ilin
Solving complex planning problems has been a long-standing challenge in computer science. Learning-based subgoal search methods have shown promise in tackling these problems, but t…
Optimistic Multi-Agent Policy Gradient
Wenshuai Zhao, Yi Zhao, Zhiyuan Li +2
*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior…
Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
Zhang-Wei Hong, Aviral Kumar, Sathwik Karnik +6
Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using r…
Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning
Pascal Klink, Florian Wolf, Kai Ploeger +2
Reinforcement Learning (RL) allows learning non-trivial robot control laws purely from data. However, many successful applications of RL have relied on ad-hoc regularizations, such…
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…
Sparse Function-space Representation of Neural Networks
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that mitigates these issues by converting NNs from weig…
Exploiting Local Observations for Robust Robot Learning
Wenshuai Zhao, Eetu-Aleksi Rantala, Sahar Salimpour +3
While many robotic tasks can be addressed using either centralized single-agent control with full state observation or decentralized multi-agent control, clear criteria for choosin…
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…
Suicidal Pedestrian: Generation of Safety-Critical Scenarios for Autonomous Vehicles
Yuhang Yang, Kalle Kujanpaa, Amin Babadi +2
Developing reliable autonomous driving algorithms poses challenges in testing, particularly when it comes to safety-critical traffic scenarios involving pedestrians. An open questi…
Towards Energy Efficient Control for Commercial Heavy-Duty Mobile Cranes: Modeling Hydraulic Pressures using Machine Learning
Abdolreza Taheri, Robert Pettersson, Pelle Gustafsson +2
A sizable part of the fleet of heavy-duty machinery in the construction equipment industry uses the conventional valve-controlled load-sensing hydraulics. Rigorous climate actions…
Simplified Temporal Consistency Reinforcement Learning
Yi Zhao, Wenshuai Zhao, Rinu Boney +2
Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficienc…
Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation
Wenyan Yang, Alexandre Angleraud, Roel S. Pieters +2
Robot control for tactile feedback-based manipulation can be difficult due to the modeling of physical contacts, partial observability of the environment, and noise in perception a…
Prioritized offline Goal-swapping Experience Replay
Wenyan Yang, Joni Pajarinen, Dinging Cai +1
In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number…
Swapped goal-conditioned offline reinforcement learning
Wenyan Yang, Huiling Wang, Dingding Cai +2
Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propos…
Hierarchical Imitation Learning with Vector Quantized Models
Kalle Kujanpää, Joni Pajarinen, Alexander Ilin
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-leve…