Profiles2020-2025
Adish Singla
Max Planck Institute for Software Systems
13Papers
7Last author
27Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers13
- Program Synthesis Benchmark for Visual Programming in XLogoOnline EnvironmentAuthor 3 of 3ACL 2025 · 6 citations
- Formal Models of Active Learning from Contrastive ExamplesAuthor 3 of 5NeurIPS 2025 · 2 citations
- Hints Help Finding and Fixing Bugs Differently in Python and Text-Based Program RepresentationsAuthor 4 of 5ICSE 2025 · 1 citation
- Online Reinforcement Learning with Uncertain Episode LengthsAuthor 4 of 5AAAI 2023 · 9 citations
- Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse RewardsAuthor 3 of 3NeurIPS 2022 · 122 citations
- Provable Defense against Backdoor Policies in Reinforcement LearningAuthor 3 of 4NeurIPS 2022 · 37 citations
- Admissible Policy Teaching through Reward DesignAuthor 2 of 4AAAI 2022 · 18 citations
- On Batch Teaching with Sample Complexity Bounded by VCDAuthor 3 of 4NeurIPS 2022 · 6 citations
- Explicable Reward Design for Reinforcement Learning AgentsAuthor 4 of 4NeurIPS 2021 · 60 citations
- Curriculum Design for Teaching via Demonstrations: Theory and ApplicationsAuthor 4 of 4NeurIPS 2021 · 10 citations
- Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries ParadigmAuthor 3 of 3NeurIPS 2021 · 4 citations
- Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement LearningAuthor 5 of 5ICML 2020 · 145 citations
- Synthesizing Tasks for Block-based ProgrammingAuthor 7 of 7NeurIPS 2020 · 26 citations
