Goran Radanovic

94 papers A* 24A 12B 2C 2Journal 50Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	AgenticRed: Optimizing Agentic Systems for Automated Red-teaming. CoRR Jiayi Yuan, Jonathan Nöther, Natasha Jaques, Goran Radanovic
2026	J	`jnl`	Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback. CoRR Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
2026	J	`jnl`	MaMa: A Game-Theoretic Approach for Designing Safe Agentic Systems. CoRR Jonathan Nöther, Adish Singla, Goran Radanovic
2025	J	`jnl`	Benchmarking the Robustness of Agentic Systems to Adversarially-Induced Harms. CoRR Jonathan Nöther, Adish Singla, Goran Radanovic
2025	J	`jnl`	Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks? CoRR Paulius Sasnauskas, Yigit Yalin, Goran Radanovic
2025	A	`conf`	Corruption Robust Offline Reinforcement Learning with Human Feedback. AISTATS Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
2025	A*	`conf`	Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making. ICML Stelios Triantafyllou, Aleksa Sukovic, Yasaman Zolfimoselo, Goran Radanovic
2025	J	`jnl`	Distributionally Robust Reinforcement Learning with Human Feedback. CoRR Debmalya Mandal, Paulius Sasnauskas, Goran Radanovic
2025	A	`conf`	Independent Learning in Performative Markov Potential Games. AISTATS Rilind Sahitaj, Paulius Sasnauskas, Yigit Yalin, Debmalya Mandal, Goran Radanovic
2025	J	`jnl`	Independent Learning in Performative Markov Potential Games. CoRR Rilind Sahitaj, Paulius Sasnauskas, Yigit Yalin, Debmalya Mandal, Goran Radanovic
2025	A*	`conf`	On Corruption-Robustness in Performative Reinforcement Learning. AAAI Vasilis Pollatos, Debmalya Mandal, Goran Radanovic
2025	J	`jnl`	On Corruption-Robustness in Performative Reinforcement Learning. CoRR Vasilis Pollatos, Debmalya Mandal, Goran Radanovic
2025	A	`conf`	Performative Reinforcement Learning with Linear Markov Decision Process. AISTATS Debmalya Mandal, Goran Radanovic
2025	A	`conf`	Policy Teaching via Data Poisoning in Learning from Human Preferences. AISTATS Andi Nika, Jonathan Nöther, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
2025	J	`jnl`	Policy Teaching via Data Poisoning in Learning from Human Preferences. CoRR Andi Nika, Jonathan Nöther, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
2025	J	`jnl`	Reinforcement Learning for Durable Algorithmic Recourse. CoRR Marina Ceccon, Alessandro Fabris, Goran Radanovic, Asia J. Biega, Gian Antonio Susto
2025	J	`jnl`	Sparse Offline Reinforcement Learning with Corruption Robustness. CoRR Nam Phuong Tran, Andi Nika, Goran Radanovic, Long Tran-Thanh, Debmalya Mandal
2025	A*	`conf`	Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints. AAAI Jonathan Nöther, Adish Singla, Goran Radanovic
2025	J	`jnl`	Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints. CoRR Jonathan Nöther, Adish Singla, Goran Radanovic
2024	A*	`conf`	Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs. ICML Stelios Triantafyllou, Aleksa Sukovic, Debmalya Mandal, Goran Radanovic
2024	J	`jnl`	Corruption Robust Offline Reinforcement Learning with Human Feedback. CoRR Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban, Adish Singla, Goran Radanovic
2024	A	`conf`	Corruption-Robust Offline Two-Player Zero-Sum Markov Games. AISTATS Andi Nika, Debmalya Mandal, Adish Singla, Goran Radanovic
2024	J	`jnl`	Corruption-Robust Offline Two-Player Zero-Sum Markov Games. CoRR Andi Nika, Debmalya Mandal, Adish Singla, Goran Radanovic
2024	J	`jnl`	Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making. CoRR Stelios Triantafyllou, Aleksa Sukovic, Yasaman Zolfimoselo, Goran Radanovic
2024	J	`jnl`	Defending Against Unknown Corrupted Agents: Reinforcement Learning of Adversarially Robust Nash Equilibria. Trans. Mach. Learn. Res. Andi Nika, Jonathan Nöther, Adish Singla, Goran Radanovic
2024	A*	`conf`	Learning Embeddings for Sequential Tasks Using Population of Agents. IJCAI Mridul Mahajan, Georgios Tzannetos, Goran Radanovic, Adish Singla
2024	A	`conf`	Performative Reinforcement Learning in Gradually Shifting Environments. UAI Ben Rank, Stelios Triantafyllou, Debmalya Mandal, Goran Radanovic
2024	J	`jnl`	Performative Reinforcement Learning in Gradually Shifting Environments. CoRR Ben Rank, Stelios Triantafyllou, Debmalya Mandal, Goran Radanovic
2024	J	`jnl`	Performative Reinforcement Learning with Linear Markov Decision Process. CoRR Debmalya Mandal, Goran Radanovic
2024	A*	`conf`	Reward Design for Justifiable Sequential Decision-Making. ICLR Aleksa Sukovic, Goran Radanovic
2024	J	`jnl`	Reward Design for Justifiable Sequential Decision-Making. CoRR Aleksa Sukovic, Goran Radanovic
2024	A*	`conf`	Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences. ICML Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Georgios Tzannetos, Goran Radanovic, Adish Singla
2024	J	`jnl`	Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences. CoRR Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Georgios Tzannetos, Goran Radanovic, Adish Singla
2023	J	`jnl`	Agent-Specific Effects. CoRR Stelios Triantafyllou, Aleksa Sukovic, Debmalya Mandal, Goran Radanovic
2023	J	`jnl`	Defense Against Reward Poisoning Attacks in Reinforcement Learning. Trans. Mach. Learn. Res. Kiarash Banihashem, Adish Singla, Goran Radanovic
2023	A	`conf`	Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks. AAMAS Mohammad Mohammadi, Jonathan Nöther, Debmalya Mandal, Adish Singla, Goran Radanovic
2023	J	`jnl`	Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks. CoRR Mohammad Mohammadi, Jonathan Nöther, Debmalya Mandal, Adish Singla, Goran Radanovic
2023	J	`jnl`	Learning Embeddings for Sequential Tasks Using Population of Agents. CoRR Mridul Mahajan, Georgios Tzannetos, Goran Radanovic, Adish Singla
2023	A*	`conf`	Markov Decision Processes with Time-Varying Geometric Discounting. AAAI Jiarui Gan, Annika Hennes, Rupak Majumdar, Debmalya Mandal, Goran Radanovic
2023	J	`jnl`	Markov Decision Processes with Time-Varying Geometric Discounting. CoRR Jiarui Gan, Annika Hennes, Rupak Majumdar, Debmalya Mandal, Goran Radanovic
2023	A	`conf`	Online Defense Strategies for Reinforcement Learning Against Adaptive Reward Poisoning. AISTATS Andi Nika, Adish Singla, Goran Radanovic
2023	A*	`conf`	Online Reinforcement Learning with Uncertain Episode Lengths. AAAI Debmalya Mandal, Goran Radanovic, Jiarui Gan, Adish Singla, Rupak Majumdar
2023	J	`jnl`	Online Reinforcement Learning with Uncertain Episode Lengths. CoRR Debmalya Mandal, Goran Radanovic, Jiarui Gan, Adish Singla, Rupak Majumdar
2023	A*	`conf`	Performative Reinforcement Learning. ICML Debmalya Mandal, Stelios Triantafyllou, Goran Radanovic
2023	J	`jnl`	Sequential Principal-Agent Problems with Communication: Efficient Computation and Learning. CoRR Jiarui Gan, Rupak Majumdar, Debmalya Mandal, Goran Radanovic
2023	A	`conf`	Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs. AAMAS Stelios Triantafyllou, Goran Radanovic
2023	J	`jnl`	Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs. CoRR Stelios Triantafyllou, Goran Radanovic
2022	C	`conf`	Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes. AIES Stelios Triantafyllou, Adish Singla, Goran Radanovic
2022	J	`jnl`	Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes. CoRR Stelios Triantafyllou, Adish Singla, Goran Radanovic
2022	A*	`conf`	Admissible Policy Teaching through Reward Design. AAAI Kiarash Banihashem, Adish Singla, Jiarui Gan, Goran Radanovic
2022	J	`jnl`	Admissible Policy Teaching through Reward Design. CoRR Kiarash Banihashem, Adish Singla, Jiarui Gan, Goran Radanovic
2022	A*	`conf`	Bayesian Persuasion in Sequential Decision-Making. AAAI Jiarui Gan, Rupak Majumdar, Goran Radanovic, Adish Singla
2022	A*	`conf`	Envy-free Policy Teaching to Multiple Agents. NeurIPS Jiarui Gan, Rupak Majumdar, Adish Singla, Goran Radanovic
2022	J	`jnl`	Performative Reinforcement Learning. CoRR Debmalya Mandal, Stelios Triantafyllou, Goran Radanovic
2022	B	`conf`	Sequential Decision Making With Information Asymmetry (Invited Talk). CONCUR Jiarui Gan, Rupak Majumdar, Goran Radanovic, Adish Singla
2021	J	`jnl`	Bayesian Persuasion in Sequential Decision-Making. CoRR Jiarui Gan, Rupak Majumdar, Goran Radanovic, Adish Singla
2021	J	`jnl`	Defense Against Reward Poisoning Attacks in Reinforcement Learning. CoRR Kiarash Banihashem, Adish Singla, Goran Radanovic
2021	J	`jnl`	Diversity in News Recommendation (Dagstuhl Perspectives Workshop 19482). Dagstuhl Manifestos Abraham Bernstein, Claes H. de Vreese, Natali Helberger, Wolfgang Schulz, Katharina A. Zweig, Christian Baden, Michael A. Beam, Marc P. Hauer, Lucien Heitz, Pascal Jürgens, Christian Katzenbach, Benjamin Kille, Beate Klimkiewicz, Wiebke Loosen, Judith Möller, Goran Radanovic, Guy Shani, Nava Tintarev, Suzanne Tolmeijer, Wouter van Atteveldt, Sanne Vrijenhoek, Theresa Zueger
2021	A*	`conf`	Explicable Reward Design for Reinforcement Learning Agents. NeurIPS Rati Devidze, Goran Radanovic, Parameswaran Kamalaruban, Adish Singla
2021	A	`conf`	Learning Robust Helpful Behaviors in Two-Player Cooperative Atari Environments. AAMAS Paul Tylkin, Goran Radanovic, David C. Parkes
2021	A*	`conf`	On Blame Attribution for Accountable Multi-Agent Sequential Decision Making. NeurIPS Stelios Triantafyllou, Adish Singla, Goran Radanovic
2021	J	`jnl`	On Blame Attribution for Accountable Multi-Agent Sequential Decision Making. CoRR Stelios Triantafyllou, Adish Singla, Goran Radanovic
2021	J	`jnl`	Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks. J. Mach. Learn. Res. Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
2021	J	`jnl`	Reinforcement Learning for Education: Opportunities and Challenges. CoRR Adish Singla, Anna N. Rafferty, Goran Radanovic, Neil T. Heffernan
2020	J	`jnl`	Diversity in News Recommendations. CoRR Abraham Bernstein, Claes H. de Vreese, Natali Helberger, Wolfgang Schulz, Katharina A. Zweig, Christian Baden, Michael A. Beam, Marc P. Hauer, Lucien Heitz, Pascal Jürgens, Christian Katzenbach, Benjamin Kille, Beate Klimkiewicz, Wiebke Loosen, Judith Möller, Goran Radanovic, Guy Shani, Nava Tintarev, Suzanne Tolmeijer, Wouter van Atteveldt, Sanne Vrijenhoek, Theresa Zueger
2020	J	`jnl`	How do fairness definitions fare? Testing public attitudes towards three algorithmic definitions of fairness in loan allocations. Artif. Intell. Nripsuta Ani Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David C. Parkes, Yang Liu
2020	J	`jnl`	Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks. CoRR Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
2020	A*	`conf`	Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning. ICML Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
2020	J	`jnl`	Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning. CoRR Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla
2020	A*	`conf`	The Effectiveness of Peer Prediction in Long-Term Forecasting. AAAI Debmalya Mandal, Goran Radanovic, David C. Parkes
2019	A*	`conf`	Bayesian Fairness. AAAI Christos Dimitrakakis, Yang Liu, David C. Parkes, Goran Radanovic
2019	C	`conf`	How Do Fairness Definitions Fare?: Examining Public Attitudes Towards Algorithmic Definitions of Fairness. AIES Nripsuta Ani Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David C. Parkes, Yang Liu
2019	A*	`conf`	Learning to Collaborate in Markov Decision Processes. ICML Goran Radanovic, Rati Devidze, David C. Parkes, Adish Singla
2019	J	`jnl`	Learning to Collaborate in Markov Decision Processes. CoRR Goran Radanovic, Rati Devidze, David C. Parkes, Adish Singla
2018	J	`jnl`	How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness. CoRR Nripsuta Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David C. Parkes, Yang Liu
2018	A*	`conf`	Information Gathering With Peers: Submodular Optimization With Peer-Prediction Constraints. AAAI Goran Radanovic, Adish Singla, Andreas Krause, Boi Faltings
2018	A*	`conf`	Partial Truthfulness in Minimal Peer Prediction Mechanisms With Limited Knowledge. AAAI Goran Radanovic, Boi Faltings
2017	J	`jnl`	Calibrated Fairness in Bandits. CoRR Yang Liu, Goran Radanovic, Christos Dimitrakakis, Debmalya Mandal, David C. Parkes
2017	—	`book`	Game Theory for Data Science: Eliciting Truthful Information Game Theory for Data Science Boi Faltings, Goran Radanovic
2017	J	`jnl`	Information Gathering with Peers: Submodular Optimization with Peer-Prediction Constraints. CoRR Goran Radanovic, Adish Singla, Andreas Krause, Boi Faltings
2017	J	`jnl`	Mechanismen zur Beschaffung korrekter Daten. Inform. Spektrum Boi Faltings, Goran Radanovic
2017	—	`conf`	Multi-View Decision Processes: The Helper-AI Problem. NIPS Christos Dimitrakakis, David C. Parkes, Goran Radanovic, Paul Tylkin
2017	J	`jnl`	Partial Truthfulness in Minimal Peer Prediction Mechanisms with Limited Knowledge. CoRR Goran Radanovic, Boi Faltings
2017	J	`jnl`	Peer Truth Serum: Incentives for Crowdsourcing Measurements and Opinions. CoRR Boi Faltings, Radu Jurca, Goran Radanovic
2017	J	`jnl`	Subjective fairness: Fairness is in the eye of the beholder. CoRR Christos Dimitrakakis, Yang Liu, David C. Parkes, Goran Radanovic
2016	—	`—`	Elicitation and Aggregation of Crowd Information. Goran Radanovic
2016	J	`jnl`	Incentives for Effort in Crowdsourcing Using the Peer Truth Serum. ACM Trans. Intell. Syst. Technol. Goran Radanovic, Boi Faltings, Radu Jurca
2016	B	`conf`	Learning to Scale Payments in Crowdsourcing with PropeRBoost. HCOMP Goran Radanovic, Boi Faltings
2016	A	`conf`	Limiting the Influence of Low Quality Information in Community Sensing. AAMAS Goran Radanovic, Boi Faltings
2015	A	`conf`	Incentive Schemes for Participatory Sensing. AAMAS Goran Radanovic, Boi Faltings
2015	A*	`conf`	Incentives for Subjective Evaluations with Private Beliefs. AAAI Goran Radanovic, Boi Faltings
2015	—	`conf`	Incentivizing truthful responses with the logarithmic peer truth serum. UbiComp/ISWC Adjunct Goran Radanovic, Boi Faltings
2014	A*	`conf`	Incentives for Truthful Information Elicitation of Continuous Signals. AAAI Goran Radanovic, Boi Faltings
2013	A*	`conf`	A Robust Bayesian Truth Serum for Non-Binary Signals. AAAI Goran Radanovic, Boi Faltings