Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards von Pitis, Silviu

Volltext bestellen

Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards von Pitis, Silviu

Volltext

Source Traces for Temporal Difference Learning von Pitis, Silviu

Volltext bestellen

Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach von Pitis, Silviu

Volltext bestellen

Improving Context-Aware Preference Modeling for Language Models von Pitis, Silviu, Xiao, Ziang, Roux, Nicolas Le, Sordoni, Alessandro

Volltext bestellen

Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes von Pitis, Silviu, Zhang, Michael R

Volltext bestellen

Boosted Prompt Ensembles for Large Language Models von Pitis, Silviu, Zhang, Michael R, Wang, Andrew, Ba, Jimmy

Volltext bestellen

Source Traces for Temporal Difference Learning von Pitis, Silviu

Volltext

Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach von Pitis, Silviu

Volltext

Report Cards: Qualitative Evaluation of Language Models Using Natural Language Summaries von Yang, Blair, Cui, Fuyang, Paster, Keiran, Ba, Jimmy, Vaezipoor, Pashootan, Pitis, Silviu, Zhang, Michael R

Volltext bestellen

MoCoDA: Model-based Counterfactual Data Augmentation von Pitis, Silviu, Creager, Elliot, Mandlekar, Ajay, Garg, Animesh

Volltext bestellen

Counterfactual Data Augmentation using Locally Factored Dynamics von Pitis, Silviu, Creager, Elliot, Garg, Animesh

Volltext bestellen

Identifying the Risks of LM Agents with an LM-Emulated Sandbox von Ruan, Yangjun, Dong, Honghua, Wang, Andrew, Pitis, Silviu, Zhou, Yongchao, Ba, Jimmy, Dubois, Yann, Maddison, Chris J, Hashimoto, Tatsunori

Volltext bestellen

Large Language Models Are Human-Level Prompt Engineers von Zhou, Yongchao, Muresanu, Andrei Ioan, Han, Ziwen, Paster, Keiran, Pitis, Silviu, Chan, Harris, Ba, Jimmy

Volltext bestellen

Improving Context-Aware Preference Modeling for Language Models von Pitis, Silviu, Xiao, Ziang, Nicolas Le Roux, Sordoni, Alessandro

Volltext

Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning von Pitis, Silviu, Chan, Harris, Zhao, Stephen, Stadie, Bradly, Ba, Jimmy

Volltext bestellen

An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality von Pitis, Silviu, Chan, Harris, Jamali, Kiarash, Ba, Jimmy

Volltext bestellen

Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes von Pitis, Silviu, Zhang, Michael R

Volltext

Boosted Prompt Ensembles for Large Language Models von Pitis, Silviu, Zhang, Michael R, Wang, Andrew, Ba, Jimmy

Volltext

MoCoDA: Model-based Counterfactual Data Augmentation von Pitis, Silviu, Creager, Elliot, Mandlekar, Ajay, Garg, Animesh

Volltext