Silviu Pitis

Boosted Prompt Ensembles for Large Language Models

Apr 12, 2023
Silviu Pitis, Michael R. Zhang, Andrew Wang, Jimmy Ba

Figure 2 for Boosted Prompt Ensembles for Large Language Models

Figure 3 for Boosted Prompt Ensembles for Large Language Models

Figure 4 for Boosted Prompt Ensembles for Large Language Models

Access Paper or Ask Questions

Large Language Models Are Human-Level Prompt Engineers

Nov 03, 2022
Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, Jimmy Ba

Figure 2 for Large Language Models Are Human-Level Prompt Engineers

Figure 3 for Large Language Models Are Human-Level Prompt Engineers

Figure 4 for Large Language Models Are Human-Level Prompt Engineers

Access Paper or Ask Questions

MoCoDA: Model-based Counterfactual Data Augmentation

Oct 20, 2022
Silviu Pitis, Elliot Creager, Ajay Mandlekar, Animesh Garg

Figure 2 for MoCoDA: Model-based Counterfactual Data Augmentation

Figure 3 for MoCoDA: Model-based Counterfactual Data Augmentation

Figure 4 for MoCoDA: Model-based Counterfactual Data Augmentation

* In Proceedings of NeurIPS 2022. 10 pages (+3 references, +10 appendix). Code available at https://github.com/spitis/mocoda

Access Paper or Ask Questions

Counterfactual Data Augmentation using Locally Factored Dynamics

Jul 06, 2020
Silviu Pitis, Elliot Creager, Animesh Garg

Figure 2 for Counterfactual Data Augmentation using Locally Factored Dynamics

Figure 3 for Counterfactual Data Augmentation using Locally Factored Dynamics

Figure 4 for Counterfactual Data Augmentation using Locally Factored Dynamics

* 12 pages (+12 appendix). Code available at \url{https://github.com/spitis/mrl}

Access Paper or Ask Questions

Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning

Jul 06, 2020
Silviu Pitis, Harris Chan, Stephen Zhao, Bradly Stadie, Jimmy Ba

Figure 2 for Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning

Figure 3 for Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning

Figure 4 for Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning

* 12 pages (+12 appendix). Published as a conference paper at ICML 2020. Code available at https://github.com/spitis/mrl

Access Paper or Ask Questions

An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality

Feb 14, 2020
Silviu Pitis, Harris Chan, Kiarash Jamali, Jimmy Ba

Figure 2 for An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality

Figure 3 for An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality

Figure 4 for An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality

* 11 pages (+18 appendix). Published as a conference paper at ICLR 2020. https://openreview.net/forum?id=HJeiDpVFPr

Access Paper or Ask Questions

Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes

Jan 27, 2020
Silviu Pitis, Michael R. Zhang

Figure 2 for Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes

Figure 3 for Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes

Figure 4 for Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes

* 10 pages, 3 figures. To appear in proceedings of AAMAS 2020

Access Paper or Ask Questions

Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning

Sep 09, 2019
Kristopher De Asis, Alan Chan, Silviu Pitis, Richard S. Sutton, Daniel Graves

Figure 2 for Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning

Figure 3 for Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning

Figure 4 for Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning

Access Paper or Ask Questions

Source Traces for Temporal Difference Learning

Feb 08, 2019
Silviu Pitis

Figure 2 for Source Traces for Temporal Difference Learning

Figure 3 for Source Traces for Temporal Difference Learning

Figure 4 for Source Traces for Temporal Difference Learning

* 8 pages. In proceedings of AAAI 2018. Slides and bibtex available at https://silviupitis.com/#source-traces-for-temporal-difference-learning

Access Paper or Ask Questions

Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach

Feb 08, 2019
Silviu Pitis

Figure 2 for Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach

Figure 3 for Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach

* 8 pages + 1 page supplement. In proceedings of AAAI 2019. Slides, poster and bibtex available at https://silviupitis.com/#rethinking-the-discount-factor-in-reinforcement-learning-a-decision-theoretic-approach

Access Paper or Ask Questions