Jason Pazis

16 papers A* 8A 1Journal 3Unranked 3
YearRankTypeTitle / Venue / Authors
2020 J jnl
Crossmodal attentive skill learner: learning in Atari and beyond with audio-video inputs.
Auton. Agents Multi Agent Syst.
Dong-Ki Kim, Shayegan Omidshafiei, Jason Pazis, Jonathan P. How
2018 A conf
Crossmodal Attentive Skill Learner.
AAMAS
Shayegan Omidshafiei, Dong-Ki Kim, Jason Pazis, Jonathan P. How
2017 J jnl
Crossmodal Attentive Skill Learner.
CoRR
Shayegan Omidshafiei, Dong-Ki Kim, Jason Pazis, Jonathan P. How
2017 A* conf
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability.
ICML
Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How, John Vian
2017 J jnl
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability.
CoRR
Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How, John Vian
2017 A* conf
Duckietown: An open, inexpensive and flexible platform for autonomy education and research.
ICRA
Liam Paull, Jacopo Tani, Heejin Ahn, Javier Alonso-Mora, Luca Carlone, Michal Cáp, Yu Fan Chen, Changhyun Choi, Jeff Dusek, Yajun Fang, Daniel Hoehener, Shih-Yuan Liu, Michael Novitzky, Igor Franzoni Okuyama, Jason Pazis, Guy Rosman, Valerio Varricchio, Hsueh-Cheng Wang, Dmitry S. Yershov, Hang Zhao, Michael Benjamin, Christopher Carr, Maria T. Zuber, Sertac Karaman, Emilio Frazzoli, Domitilla Del Vecchio, Daniela Rus, Jonathan P. How, John J. Leonard, Andrea Censi
2016 A* conf
Efficient PAC-Optimal Exploration in Concurrent, Continuous State MDPs with Delayed Updates.
AAAI
Jason Pazis, Ronald Parr
2016 — conf
Improving PAC Exploration Using the Median Of Means.
NIPS
Jason Pazis, Ronald Parr, Jonathan P. How
2015 — —
PAC-optimal, Non-parametric Algorithms and Bounds for Exploration in Concurrent MDPs with Delayed Updates.
Jason Pazis
2013 A* conf
PAC Optimal Exploration in Continuous Space Markov Decision Processes.
AAAI
Jason Pazis, Ronald Parr
2013 A* conf
Sample Complexity and Performance Bounds for Non-Parametric Approximate Linear Programming.
AAAI
Jason Pazis, Ronald Parr
2011 A* conf
Generalized Value Functions for Large Action Sets.
ICML
Jason Pazis, Ronald Parr
2011 A* conf
Non-Parametric Approximate Linear Programming for MDPs.
AAAI
Jason Pazis, Ronald Parr
2011 — conf
Reinforcement learning in multidimensional continuous action spaces.
ADPRL
Jason Pazis, Michail G. Lagoudakis
2009 A* conf
Binary action search for learning continuous-action control policies.
ICML
Jason Pazis, Michail G. Lagoudakis
2009 — conf
Learning continuous-action control policies.
ADPRL
Jason Pazis, Michail G. Lagoudakis