Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Pablo Samuel Castro

Pablo Samuel Castro

Deep Reinforcement Learning at the Edge of the Statistical Precipice


Aug 30, 2021
Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, Aaron Courville, Marc G. Bellemare

Figure 1 for Deep Reinforcement Learning at the Edge of the Statistical Precipice
Figure 2 for Deep Reinforcement Learning at the Edge of the Statistical Precipice
Figure 3 for Deep Reinforcement Learning at the Edge of the Statistical Precipice
Figure 4 for Deep Reinforcement Learning at the Edge of the Statistical Precipice

  Access Paper or Ask Questions

A functional mirror ascent view of policy gradient methods with function approximation


Aug 12, 2021
Sharan Vaswani, Olivier Bachem, Simone Totaro, Robert Mueller, Matthieu Geist, Marlos C. Machado, Pablo Samuel Castro, Nicolas Le Roux

Figure 1 for A functional mirror ascent view of policy gradient methods with function approximation
Figure 2 for A functional mirror ascent view of policy gradient methods with function approximation
Figure 3 for A functional mirror ascent view of policy gradient methods with function approximation
Figure 4 for A functional mirror ascent view of policy gradient methods with function approximation

  Access Paper or Ask Questions

MICo: Learning improved representations via sampling-based state similarity for Markov decision processes


Jun 03, 2021
Pablo Samuel Castro, Tyler Kastner, Prakash Panangaden, Mark Rowland

Figure 1 for MICo: Learning improved representations via sampling-based state similarity for Markov decision processes
Figure 2 for MICo: Learning improved representations via sampling-based state similarity for Markov decision processes
Figure 3 for MICo: Learning improved representations via sampling-based state similarity for Markov decision processes
Figure 4 for MICo: Learning improved representations via sampling-based state similarity for Markov decision processes

  Access Paper or Ask Questions

Metrics and continuity in reinforcement learning


Feb 02, 2021
Charline Le Lan, Marc G. Bellemare, Pablo Samuel Castro

Figure 1 for Metrics and continuity in reinforcement learning
Figure 2 for Metrics and continuity in reinforcement learning
Figure 3 for Metrics and continuity in reinforcement learning
Figure 4 for Metrics and continuity in reinforcement learning
* Accepted at AAAI 2021 
  Access Paper or Ask Questions

Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning


Jan 13, 2021
Rishabh Agarwal, Marlos C. Machado, Pablo Samuel Castro, Marc G. Bellemare

Figure 1 for Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
Figure 2 for Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
Figure 3 for Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
Figure 4 for Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
* Accepted at ICLR 2021 (Spotlight). Website: https://agarwl.github.io/pse 
  Access Paper or Ask Questions

Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research


Nov 20, 2020
Johan S. Obando-Ceron, Pablo Samuel Castro

Figure 1 for Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Figure 2 for Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Figure 3 for Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
Figure 4 for Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research
* Deep RL Workshop, NeurIPS 2020 
  Access Paper or Ask Questions

GANterpretations


Nov 06, 2020
Pablo Samuel Castro

Figure 1 for GANterpretations
* In 4th Workshop on Machine Learning for Creativity and Design at NeurIPS 2020, Vancouver, Canada 
  Access Paper or Ask Questions

Rigging the Lottery: Making All Tickets Winners


Nov 25, 2019
Utku Evci, Trevor Gale, Jacob Menick, Pablo Samuel Castro, Erich Elsen

Figure 1 for Rigging the Lottery: Making All Tickets Winners
Figure 2 for Rigging the Lottery: Making All Tickets Winners
Figure 3 for Rigging the Lottery: Making All Tickets Winners
Figure 4 for Rigging the Lottery: Making All Tickets Winners

  Access Paper or Ask Questions

Scalable methods for computing state similarity in deterministic Markov Decision Processes


Nov 21, 2019
Pablo Samuel Castro

Figure 1 for Scalable methods for computing state similarity in deterministic Markov Decision Processes
Figure 2 for Scalable methods for computing state similarity in deterministic Markov Decision Processes
Figure 3 for Scalable methods for computing state similarity in deterministic Markov Decision Processes
Figure 4 for Scalable methods for computing state similarity in deterministic Markov Decision Processes
* To appear in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) 
  Access Paper or Ask Questions

Inverse Reinforcement Learning with Multiple Ranked Experts


Jul 31, 2019
Pablo Samuel Castro, Shijian Li, Daqing Zhang

Figure 1 for Inverse Reinforcement Learning with Multiple Ranked Experts
Figure 2 for Inverse Reinforcement Learning with Multiple Ranked Experts
Figure 3 for Inverse Reinforcement Learning with Multiple Ranked Experts
Figure 4 for Inverse Reinforcement Learning with Multiple Ranked Experts

  Access Paper or Ask Questions

Performing Structured Improvisations with pre-trained Deep Learning Models


Apr 30, 2019
Pablo Samuel Castro

Figure 1 for Performing Structured Improvisations with pre-trained Deep Learning Models
Figure 2 for Performing Structured Improvisations with pre-trained Deep Learning Models
Figure 3 for Performing Structured Improvisations with pre-trained Deep Learning Models
Figure 4 for Performing Structured Improvisations with pre-trained Deep Learning Models

  Access Paper or Ask Questions

A Comparative Analysis of Expected and Distributional Reinforcement Learning


Feb 21, 2019
Clare Lyle, Pablo Samuel Castro, Marc G. Bellemare

Figure 1 for A Comparative Analysis of Expected and Distributional Reinforcement Learning
Figure 2 for A Comparative Analysis of Expected and Distributional Reinforcement Learning
Figure 3 for A Comparative Analysis of Expected and Distributional Reinforcement Learning
Figure 4 for A Comparative Analysis of Expected and Distributional Reinforcement Learning
* To appear in the Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence 
  Access Paper or Ask Questions

Distributional reinforcement learning with linear function approximation


Feb 08, 2019
Marc G. Bellemare, Nicolas Le Roux, Pablo Samuel Castro, Subhodeep Moitra

Figure 1 for Distributional reinforcement learning with linear function approximation
Figure 2 for Distributional reinforcement learning with linear function approximation
* Proceedings of AISTATS 2019 
 * To appear 
  Access Paper or Ask Questions

A Geometric Perspective on Optimal Representations for Reinforcement Learning


Jan 31, 2019
Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taiga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle

Figure 1 for A Geometric Perspective on Optimal Representations for Reinforcement Learning
Figure 2 for A Geometric Perspective on Optimal Representations for Reinforcement Learning
Figure 3 for A Geometric Perspective on Optimal Representations for Reinforcement Learning
Figure 4 for A Geometric Perspective on Optimal Representations for Reinforcement Learning

  Access Paper or Ask Questions

Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue


Jan 31, 2019
Kory W. Mathewson, Pablo Samuel Castro, Colin Cherry, George Foster, Marc G. Bellemare

Figure 1 for Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
Figure 2 for Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
Figure 3 for Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
Figure 4 for Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue
* 20 pages, 9 figures 
  Access Paper or Ask Questions

An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents


Dec 17, 2018
Felipe Petroski Such, Vashisht Madhavan, Rosanne Liu, Rui Wang, Pablo Samuel Castro, Yulun Li, Ludwig Schubert, Marc Bellemare, Jeff Clune, Joel Lehman

Figure 1 for An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
Figure 2 for An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
Figure 3 for An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
Figure 4 for An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents

  Access Paper or Ask Questions

Dopamine: A Research Framework for Deep Reinforcement Learning


Dec 14, 2018
Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar, Marc G. Bellemare

Figure 1 for Dopamine: A Research Framework for Deep Reinforcement Learning
Figure 2 for Dopamine: A Research Framework for Deep Reinforcement Learning
Figure 3 for Dopamine: A Research Framework for Deep Reinforcement Learning
Figure 4 for Dopamine: A Research Framework for Deep Reinforcement Learning

  Access Paper or Ask Questions

Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation


Nov 12, 2018
Pablo Samuel Castro, Maria Attarian

Figure 1 for Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation
Figure 2 for Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation
Figure 3 for Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation
* Extended abstract (2 pages) for the NIPS 2018 Second Workshop on Machine Learning for Creativity and Design 
  Access Paper or Ask Questions

Methods for computing state similarity in Markov Decision Processes


Jun 27, 2012
Norman Ferns, Pablo Samuel Castro, Doina Precup, Prakash Panangaden

Figure 1 for Methods for computing state similarity in Markov Decision Processes
Figure 2 for Methods for computing state similarity in Markov Decision Processes
Figure 3 for Methods for computing state similarity in Markov Decision Processes
Figure 4 for Methods for computing state similarity in Markov Decision Processes
* Appears in Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI2006) 
  Access Paper or Ask Questions