Search Results - "Pazis, Jason"

Crossmodal attentive skill learner: learning in Atari and beyond with audio–video inputs by Kim, Dong-Ki, Omidshafiei, Shayegan, Pazis, Jason, How, Jonathan P.

“…This paper introduces the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic architecture…”
Get full text

PAC-optimal, Non-parametric Algorithms and Bounds for Exploration in Concurrent MDPs with Delayed Updates by Pazis, Jason

“…As the reinforcement learning community has shifted its focus from heuristic methods to methods that have performance guarantees, PAC-optimal exploration…”
Get full text

Duckietown: An open, inexpensive and flexible platform for autonomy education and research by Paull, Liam, Tani, Jacopo, Ahn, Heejin, Alonso-Mora, Javier, Carlone, Luca, Cap, Michal, Yu Fan Chen, Changhyun Choi, Dusek, Jeff, Yajun Fang, Hoehener, Daniel, Shih-Yuan Liu, Novitzky, Michael, Okuyama, Igor Franzoni, Pazis, Jason, Rosman, Guy, Varricchio, Valerio, Hsueh-Cheng Wang, Yershov, Dmitry, Zhao, Hang, Benjamin, Michael, Carr, Christopher, Zuber, Maria, Karaman, Sertac, Frazzoli, Emilio, Del Vecchio, Domitilla, Rus, Daniela, How, Jonathan, Leonard, John, Censi, Andrea

“…Duckietown is an open, inexpensive and flexible platform for autonomy education and research. The platform comprises small autonomous vehicles ("Duckiebots")…”
Get full text

Non-parametric Approximate Linear Programming for MDPs by Pazis, Jason

“…One of the most difficult tasks in value function based methods for learning in Markov Decision Processes is finding an approximation architecture that is…”
Get full text

Crossmodal Attentive Skill Learner by Omidshafiei, Shayegan, Kim, Dong-Ki, Pazis, Jason, How, Jonathan P

“…This paper presents the Crossmodal Attentive Skill Learner (CASL), integrated with the recently-introduced Asynchronous Advantage Option-Critic (A2OC)…”
Get full text

Reinforcement learning in multidimensional continuous action spaces by Pazis, J., Lagoudakis, M. G.

“…The majority of learning algorithms available today focus on approximating the state (V ) or state-action (Q) value function and efficient action selection…”
Get full text

Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability by Omidshafiei, Shayegan, Pazis, Jason, Amato, Christopher, How, Jonathan P, Vian, John

“…Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Sydney, Australia, PMLR 70:2681-2690, 2017 Many real-world tasks involve…”
Get full text

Learning continuous-action control policies by Pazis, J., Lagoudakis, M.G.

“…Reinforcement learning for control in stochastic processes has received significant attention in the last few years. Several data-efficient methods, even for…”
Get full text