activity
20162022
most citedDeep Predictive Policy Training using Reinforcement Learning

16 citations · 18 across the 7 of their papers we have counts for

collaborators
Showing cs.ROShow all

8 papers · 1 filter

cs.RO2021

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

Ali Ghadirzadeh, Xi Chen, Petra Poklukar +3

Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensi…

cs.RO2020

Human-centered collaborative robots with deep reinforcement learning

Ali Ghadirzadeh, Xi Chen, Wenjie Yin +3

We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk o…

cs.RO2020

Data-efficient visuomotor policy training using reinforcement learning and generative models

Ali Ghadirzadeh, Petra Poklukar, Ville Kyrki +2

We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable g…

cs.RO2019

Adversarial Feature Training for Generalizable Robotic Visuomotor Control

Xi Chen, Ali Ghadirzadeh, Mårten Björkman +1

Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's applica…

cs.RO2019

Affordance Learning for End-to-End Visuomotor Robot Control

Aleksi Hämäläinen, Karol Arndt, Ali Ghadirzadeh +1

Training end-to-end deep robot policies requires a lot of domain-, task-, and hardware-specific data, which is often costly to provide. In this work, we propose to tackle this issu…

cs.RO2018

Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments

Xi Chen, Ali Ghadirzadeh, John Folkesson +1

Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to r…