Search Results for author: Davide Tateo

Found 25 papers, 13 papers with code

Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning

1 code implementation18 Sep 2024 Jonas Günster, Puze Liu, Jan Peters, Davide Tateo

Safety is one of the key issues preventing the deployment of reinforcement learning techniques in real-world robots.

reinforcement-learning Reinforcement Learning +2

One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion

1 code implementation10 Sep 2024 Nico Bohlinger, Grzegorz Czechmanowski, Maciej Krupka, Piotr Kicki, Krzysztof Walas, Jan Peters, Davide Tateo

Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world.

Deep Reinforcement Learning reinforcement-learning

Safe and Efficient Path Planning under Uncertainty via Deep Collision Probability Fields

no code implementations6 Sep 2024 Felix Herrmann, Sebastian Zach, Jacopo Banfi, Jan Peters, Georgia Chalvatzaki, Davide Tateo

Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning.

Autonomous Driving

Bridging the gap between Learning-to-plan, Motion Primitives and Safe Reinforcement Learning

no code implementations26 Aug 2024 Piotr Kicki, Davide Tateo, Puze Liu, Jonas Guenster, Jan Peters, Krzysztof Walas

We evaluate our approach against state-of-the-art safe reinforcement learning methods, showing that our technique, particularly when exploiting task structure, outperforms baseline methods in challenging scenarios such as planning to hit in robot air hockey.

reinforcement-learning Reinforcement Learning +2

ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning

1 code implementation28 Jun 2024 Christopher E. Mower, Yuhui Wan, Hongzhan Yu, Antoine Grosnit, Jonas Gonzalez-Billandon, Matthieu Zimmer, Jinlong Wang, Xinyu Zhang, Yao Zhao, Anbang Zhai, Puze Liu, Daniel Palenicek, Davide Tateo, Cesar Cadena, Marco Hutter, Jan Peters, Guangjian Tian, Yuzheng Zhuang, Kun Shao, Xingyue Quan, Jianye Hao, Jun Wang, Haitham Bou-Ammar

Key features of the framework include: integration of ROS with an AI agent connected to a plethora of open-source and commercial LLMs, automatic extraction of a behavior from the LLM output and execution of ROS actions/services, support for three behavior modes (sequence, behavior tree, state machine), imitation learning for adding new robot actions to the library of possible actions, and LLM reflection via human and environment feedback.

AI Agent Imitation Learning

Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications

no code implementations13 Apr 2024 Puze Liu, Haitham Bou-Ammar, Jan Peters, Davide Tateo

Indeed, safety specifications, often represented as constraints, can be complex and non-linear, making safety challenging to guarantee in learning systems.

reinforcement-learning Reinforcement Learning +1

Sharing Knowledge in Multi-Task Deep Reinforcement Learning

1 code implementation ICLR 2020 Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters

We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning.

Deep Reinforcement Learning reinforcement-learning

Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot

no code implementations13 Nov 2023 Luca Lach, Robert Haschke, Davide Tateo, Jan Peters, Helge Ritter, Júlia Borràs, Carme Torras

The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks.

Deep Reinforcement Learning Inductive Bias

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies

no code implementations7 Nov 2023 Firas Al-Hafez, Guoping Zhao, Jan Peters, Davide Tateo

Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure.

continuous-control Continuous Control +4

LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning

1 code implementation1 Mar 2023 Firas Al-Hafez, Davide Tateo, Oleg Arenz, Guoping Zhao, Jan Peters

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function.

Continuous Control Imitation Learning +5

Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks

1 code implementation11 Jan 2023 Piotr Kicki, Puze Liu, Davide Tateo, Haitham Bou-Ammar, Krzysztof Walas, Piotr Skrzypczyński, Jan Peters

Motion planning is a mature area of research in robotics with many well-established methods based on optimization or sampling the state space, suitable for solving kinematic motion planning.

Motion Planning

Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction

no code implementations27 Sep 2022 Puze Liu, Kuo Zhang, Davide Tateo, Snehal Jauhri, Zhiyuan Hu, Jan Peters, Georgia Chalvatzaki

Our proposed approach achieves state-of-the-art performance in simulated high-dimensional and dynamic tasks while avoiding collisions with the environment.

reinforcement-learning Reinforcement Learning +3

Object Structural Points Representation for Graph-based Semantic Monocular Localization and Mapping

1 code implementation21 Jun 2022 Davide Tateo, Davide Antonio Cucci, Matteo Matteucci, Andrea Bonarini

In this paper, we propose the use of an efficient representation, based on structural points, for the geometry of objects to be used as landmarks in a monocular semantic SLAM system based on the pose-graph formulation.

Object Position +1

Dimensionality Reduction and Prioritized Exploration for Policy Search

no code implementations9 Mar 2022 Marius Memmel, Puze Liu, Davide Tateo, Jan Peters

Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level.

Dimensionality Reduction

Learning Stable Vector Fields on Lie Groups

no code implementations22 Oct 2021 Julen Urain, Davide Tateo, Jan Peters

Learning robot motions from demonstration requires models able to specify vector fields for the full robot pose when the task is defined in operational space.

Motion Generation

An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients

1 code implementation20 Jul 2021 João Carvalho, Davide Tateo, Fabio Muratore, Jan Peters

This estimator is unbiased, has low variance, and can be used with differentiable and non-differentiable function approximators.

ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows

no code implementations25 Oct 2020 Julen Urain, Michelle Ginesi, Davide Tateo, Jan Peters

We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics.

Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts

1 code implementation10 Jun 2020 Riad Akrour, Davide Tateo, Jan Peters

Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators.

reinforcement-learning Reinforcement Learning +1

MushroomRL: Simplifying Reinforcement Learning Research

2 code implementations4 Jan 2020 Carlo D'Eramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters

MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments.

reinforcement-learning Reinforcement Learning +1

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

1 code implementation1 Jan 2020 Simone Parisi, Davide Tateo, Maximilian Hensel, Carlo D'Eramo, Jan Peters, Joni Pajarinen

Empirical results on classic and novel benchmarks show that the proposed approach outperforms existing methods in environments with sparse rewards, especially in the presence of rewards that create suboptimal modes of the objective function.

Benchmarking reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.