Davide Tateo

Quick Info

Research Interests

Reinforcement Learning; Robotics; Deep Reinforcement Learning;

More Information

Google Scholar Curriculum Vitae

Contact Information

Mail. Davide Tateo
TU Darmstadt, Fachgebiet IAS
Hochschulstraße 10
64289 Darmstadt
Office. Room E303,
Robert-Piloty-Gebaeude S2|02
work+49-6151-16-20811


Davide Tateo is a postdoctoral researcher in the Intelligent Autonomous Systems group working on Robotics and Reinforcement Learning. Davide joined the lab in April 2019 after receiving his Ph.D. in Information Technology from Politecnico di Milano (Milan, Italy) in February 2019. He is currently working on the SKILLS4ROBOTS project, whose objective is to develop humanoid robots that can acquire and improve a rich set of motor skills.

During his Ph.D. research, Davide worked under the supervision of prof. Andrea Bonarini and prof. Marcello Restelli focusing in particular on Hierarchical and Inverse Reinforcement Learning. During his Ph.D., he also co-developed Mushroom, a Reinforcement Learning python library.

Key references

Tateo, D. (2019). Building structured hierarchical agents, Ph.D. Thesis.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Tateo, D.; ̇Erdenlig, I. S.; Bonarini, A. (2019). Graph-Based Design of Hierarchical Reinforcement Learning Agents, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Tateo, D.; Banfi, J.; Riva, A.; Amigoni, F.; Bonarini, A. (2018). Multiagent Connected Path Planning: PSPACE-Completeness and How to Deal with It, Thirty-Second AAAI Conference on Artificial Intelligence (AAAI2018), pp.4735-4742.   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Tateo, D.; D'Eramo, C.; Nuara, A.; Bonarini, A.; Restelli, M. (2017). Exploiting structure and uncertainty of Bellman updates in Markov decision processes, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

Tateo, D.; Pirotta, M.; Restelli, M.; Bonarini, A. (2017). Gradient-based minimization for multi-expert Inverse Reinforcement Learning, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).   See Details [Details]   Download Article [PDF]   BibTeX Reference [BibTex]

  

zum Seitenanfang