J. Pajarinen

发表

An Algorithmic Perspective on Imitation Learning

Pieter Abbeel, Jan Peters, J. Andrew Bagnell, 2018, Found. Trends Robotics.

Multi-agent active information gathering in discrete and continuous-state decentralized POMDPs by policy graph improvement

Jan Peters, Joni Pajarinen, Mikko Lauri, 2020, Autonomous Agents and Multi-Agent Systems.

Hybrid control trajectory optimization under uncertainty

Siddhartha S. Srinivasa, Jan Peters, Gerhard Neumann, 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Guided Reinforcement Learning Under Partial Observability

Jan Peters, J. Pajarinen, Tag der Einreichung, 2019 .

POMDPs for Continuous States and Observations for Robotics

J. Pajarinen, Sanket Shinde, 2017 .

Efficient Exploration using Value Bounds in Deep Reinforcement Learning Effiziente Exploration in Deep Reinforcement Learning mittels beschraenkter

Jan Peters, J. Pajarinen, 2019 .

Interactive Planning under Uncertainty

J. Pajarinen, Janine Hölscher, Bartolome de TirajanaSpanien, 2017 .

ProMPs Robot Trajectory Intention Prediction Belief Tracker Imitation Learning Intention Aware ProMP Adaptation Spatial Deformation Mode Temporal Scaling Mode Robot Goal Tracker Human observations Motion Goals Trajectory Predictions

Jan Peters, C. Rothkopf, Dorothea Koert, 2019 .

POMDP based manipulation planning in object composition space

V. Kyrki, J. Pajarinen, 2015 .

Visual Rewards From Observation for Sequential Tasks: Autonomous Pile Loading

J. Pajarinen, R. Ghabcheloo, Joni-Kristian Kämäräinen, 2022, Frontiers in Robotics and AI.

Self-Paced Multi-Agent Reinforcement Learning

J. Pajarinen, Wenshuai Zhao, 2022, ArXiv.

Curriculum Reinforcement Learning via Constrained Optimal Transport

J. Pajarinen, Carlo D'Eramo, Pascal Klink, 2022, ICML.

Partially Observable Markov Decision Processes in Robotics: A Survey

David Hsu, J. Pajarinen, M. Lauri, 2022, IEEE Transactions on Robotics.

Nonlinear Model Learning for Compensation and Feedforward Control of Real-World Hydraulic Actuators Using Gaussian Processes

J. Pajarinen, R. Ghabcheloo, Abdolreza Taheri, 2022, IEEE Robotics and Automation Letters.

Continuous Monte Carlo Graph Search

Juho Kannala, A. Ilin, J. Pajarinen, 2022, ArXiv.

Reinforcement Learning Based Underwater Wireless Optical Communication Alignment for Autonomous Underwater Vehicles

J. Pajarinen, R. Akrour, T. Maki, 2022, IEEE Journal of Oceanic Engineering.

Pointing Error Control of Underwater Wireless Optical Communication on Mobile Platform

J. Pajarinen, T. Maki, T. Matsuda, 2022, IEEE Photonics Technology Letters.

Redeeming Intrinsic Rewards via Constrained Optimization

Pulkit Agrawal, J. Pajarinen, Zhang-Wei Hong, 2022, NeurIPS.

Multi-agent active information gathering in discrete and continuous-state decentralized POMDPs by policy graph improvement

J. Pajarinen, M. Lauri, Jan Peters, 2020, Autonomous Agents and Multi-Agent Systems.

Decision making under uncertain segmentations

Joni Pajarinen, Ville Kyrki, V. Kyrki, 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

Deep Adversarial Reinforcement Learning for Object Disentangling

J. Peters, J. Pajarinen, O. Arenz, 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Boosted Curriculum Reinforcement Learning

J. Pajarinen, Carlo D'Eramo, Pascal Klink, 2022, ICLR.

GPU-Accelerated Policy Optimization via Batch Automatic Differentiation of Gaussian Processes for Real-World Control

J. Pajarinen, R. Ghabcheloo, Abdolreza Taheri, 2022, 2022 International Conference on Robotics and Automation (ICRA).

A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning pdf

Jan Peters, Hany Abdulsamad, Carlo D'Eramo, 2021, J. Mach. Learn. Res..

Learning in-contact control strategies from demonstration

Alberto Montebelli, Joni Pajarinen, Ville Kyrki, 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning

Jan Peters, Simone Parisi, J. Pajarinen, 2019, Algorithms.

Topological Experience Replay

Pulkit Agrawal, Tao Chen, J. Pajarinen, 2022, ICLR.

Probabilistic Approach to Physical Object Disentangling

Jan Peters, Gerhard Neumann, Joni Pajarinen, 2020, IEEE Robotics and Automation Letters.

Utilizing Human Feedback in POMDP Execution and Specification

Jan Peters, Joni Pajarinen, Janine Hoelscher, 2018, 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids).

Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation

J. Pajarinen, Joni-Kristian Kämäräinen, R. Pieters, 2023, ArXiv.

Reinforcement Learning using Guided Observability pdf

Jan Peters, Joni Pajarinen, Pascal Klink, 2021, ArXiv.

Deep Reinforcement Learning for POMDPs

J. Pajarinen, Tag der Einreichung, 2018 .

Robotic manipulation of multiple objects as a POMDP pdf

Joni Pajarinen, Ville Kyrki, V. Kyrki, 2014, Artif. Intell..

Planning under uncertainty for large-scale problems with applications to wireless networking ; Päätöksenteko epävarmuuden vallitessa suurissa ongelmissa ja sovelluksia langattomaan tiedonsiirtoon

Joni Pajarinen, J. Pajarinen, 2013 .

Deep reinforcement learning under uncertainty for autonomous driving Deep Reinforcement Learning

Jan Peters, J. Pajarinen, H. Koeppl, 2022 .

Prioritized offline Goal-swapping Experience Replay

J. Pajarinen, Joni-Kristian Kämäräinen, Wenyan Yang, 2023, ArXiv.

POMDP Planning Under Object Composition Uncertainty: Application to Robotic Manipulation

V. Kyrki, J. Pajarinen, Jens Lundell, 2023, IEEE Transactions on Robotics.

Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization

Simone Frintrop, Jan Peters, Joni Pajarinen, 2020, IEEE Robotics and Automation Letters.

Efficient Planning for Factored Infinite-Horizon DEC-POMDPs

Jaakko Peltonen, Joni Pajarinen, J. Peltonen, 2011, IJCAI.

Periodic Finite State Controllers for Efficient POMDP and DEC-POMDP Planning

Jaakko Peltonen, Joni Pajarinen, J. Peltonen, 2011, NIPS.

Projections for Approximate Policy Iteration Algorithms

Jan Peters, Gerhard Neumann, Joni Pajarinen, 2019, ICML.

Information Gathering in Decentralized POMDPs by Policy Graph Improvement

Jan Peters, Joni Pajarinen, Mikko Lauri, 2019, AAMAS.

Monte-Carlo Robot Path Planning

Jan Peters, J. Pajarinen, G. Chalvatzaki, 2022, IEEE Robotics and Automation Letters.

Learning Intention Aware Online Adaptation of Movement Primitives

Jan Peters, Susanne Trick, Dorothea Koert, 2019, IEEE Robotics and Automation Letters.

Machine Learning Based Mobile Network Throughput Classification pdf

Joni Pajarinen, Adrian Burian, Lauri Alho, 2020, 2021 IEEE Wireless Communications and Networking Conference (WCNC).

Latent Derivative Bayesian Last Layer Networks

Jan Peters, Joni Pajarinen, Pascal Klink, 2021, AISTATS.

Establishment of line-of-sight optical links between autonomous underwater vehicles: Field experiment and performance validation

J. Pajarinen, T. Maki, T. Matsuda, 2022, Applied Ocean Research.

Sim-to-Real Transfer for Underwater Wireless Optical Communication Alignment Policy between AUVs

J. Pajarinen, T. Maki, T. Matsuda, 2022, Oceans.

Self-Paced Deep Reinforcement Learning pdf

Jan Peters, Carlo D'Eramo, Joni Pajarinen, 2020, NeurIPS.

Exploration Driven by an Optimistic Bellman Equation

Jan Peters, Marcello Restelli, Carlo D'Eramo, 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

Technical Report: “Exploration Driven by an Optimistic Bellman Equation”

Jan Peters, Marcello Restelli, J. Pajarinen, 2018 .

Hierarchical Imitation Learning with Vector Quantized Models

J. Pajarinen, A. Ilin, Kalle Kujanpää, 2023, International Conference on Machine Learning.

Compatible natural gradient policy search

Jan Peters, Gerhard Neumann, Joni Pajarinen, 2019, Machine Learning.

Generalized Mean Estimation in Monte-Carlo Tree Search pdf

Jan Peters, Joni Pajarinen, Tuan Dam, 2019, IJCAI.

Continuous Monte Carlo Graph Search

Juho Kannala, A. Ilin, J. Pajarinen, 2022, AAMAS.

Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

Juho Kannala, J. Pajarinen, Rinu Boney, 2022, ESANN.

A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search

J. Pajarinen, Carlo D'Eramo, Jan Peters, 2022, ArXiv.

Optimizing Spatial and Temporal Reuse in Wireless Networks by Decentralized Partially Observable Markov Decision Processes

Ari Hottinen, Jaakko Peltonen, Joni Pajarinen, 2014, IEEE Transactions on Mobile Computing.

Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning

Jan Peters, Kai Ploeger, J. Pajarinen, 2023, ArXiv.

On the Benefit of Optimal Transport for Curriculum Reinforcement Learning

Jan Peters, J. Pajarinen, Carlo D'Eramo, 2023, ArXiv.

Monte-Carlo tree search with uncertainty propagation via optimal transport

Odalric-Ambrym Maillard, J. Pajarinen, Carlo D'Eramo, 2023, ArXiv.

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Aviral Kumar, J. Pajarinen, Zhang-Wei Hong, 2023, ArXiv.

Sparse Latent Space Policy Search

Heni Ben Amor, Joni Pajarinen, Ville Kyrki, 2016, AAAI.

Backpropagation Through Agents

J. Pajarinen, Zhiyuan Li, Wenshuai Zhao, 2024, AAAI.

AgentMixer: Multi-Agent Correlated Policy Factorization

J. Pajarinen, Zhiyuan Li, Wenshuai Zhao, 2024, ArXiv.

Optimistic Multi-Agent Policy Gradient for Cooperative Tasks

Juho Kannala, J. Pajarinen, Yi Zhao, 2023, ArXiv.

Learning Progress Driven Multi-Agent Curriculum

J. Pajarinen, Wenshuai Zhao, Zhiyuan Li, 2022, 2205.10016.

Simplified Temporal Consistency Reinforcement Learning

Juho Kannala, J. Pajarinen, Rinu Boney, 2023, ICML.

Suicidal Pedestrian: Generation of Safety-Critical Scenarios for Autonomous Vehicles

J. Pajarinen, Kalle Kujanpää, Alexander Ilin, 2023, 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC).

Function-space Parameterization of Neural Networks for Sequential Learning

Paul E. Chang, J. Pajarinen, Ella Tamir, 2024, ArXiv.

Sparse Function-space Representation of Neural Networks

Paul E. Chang, J. Pajarinen, A. Solin, 2023, ArXiv.