380 citations
- Stony Brook UniversityUS19 papers
- Northwestern UniversityUS16 papers
- University of MichiganUS14 papers
- Centre National de la Recherche ScientifiqueFR13 papers
- Flatiron Health (United States)US13 papers
- Flatiron Institute13 papers
- University of FloridaUS13 papers
- California Institute of TechnologyUS12 papers
- Fermi National Accelerator LaboratoryUS12 papers
- Los Alamos National LaboratoryUS12 papers
- Pennsylvania State UniversityUS12 papers
- University of RochesterUS12 papers
Showing 2021 · cs.AIShow all
2 papers · 2 filters
cs.AI2021
Dynamic probabilistic logic models for effective abstractions in RL
Harsha Kokel, Arjun Manoharan, Sriraam Natarajan +2
State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hie…
cs.AI2021★ 68 cited
Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
Matthew L. Olson, Roli Khanna, Lawrence Neal +2
Counterfactual explanations, which deal with "why not?" scenarios, can provide insightful explanations to an AI agent's behavior. In this work, we focus on generating counterfactua…