Profiles2021-2026
Yali Du
The Alan Turing Institute
25Papers
6Last author
67Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers25
- SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social DilemmasAuthor 6 of 6ICLR 2026 · 11 citations
- BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation GamesAuthor 6 of 6ICLR 2026
- Entropy-Aware Reshaping of Reinforcement Signals for Multi-Answer ReasoningAuthor 4 of 5ACL Findings 2026
- Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?Author 4 of 4ICLR 2026
- NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement LearningAuthor 5 of 6EMNLP 2025 · 4 citations
- Abstract Counterfactuals for Language Model AgentsAuthor 3 of 5NeurIPS 2025 · 3 citations
- Self-Verifying Reflection Helps Transformers with CoT ReasoningAuthor 6 of 7NeurIPS 2025 · 3 citations
- ATLAS: Agent Tuning via Learning Critical StepsAuthor 4 of 6ACL Findings 2025 · 2 citations
- Spiral of Silence in Large Language Model AgentsAuthor 6 of 8EMNLP Findings 2025 · 1 citation
- CODI: Compressing Chain-of-Thought into Continuous Space via Self-DistillationAuthor 5 of 6EMNLP 2025
- On the Optimization Landscape of Low Rank Adaptation Methods for Large Language ModelsAuthor 2 of 4ICLR 2025
- Self-Guiding Exploration for Combinatorial ProblemsAuthor 2 of 4NeurIPS 2024 · 27 citations
- STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement LearningAuthor 4 of 4AAAI 2024 · 11 citations
- PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic ManipulationAuthor 2 of 5ICML 2024 · 10 citations
- Policy Learning from Tutorial Books via Understanding, Rehearsing and IntrospectingAuthor 3 of 7NeurIPS 2024 · 4 citations
- TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy GradientAuthor 5 of 5AAAI 2024 · 2 citations
- Learning the Expected Core of Strictly Convex Stochastic Cooperative GamesAuthor 6 of 7NeurIPS 2024 · 1 citation
- Invariant Learning via Probability of Sufficient and Necessary CausesAuthor 4 of 8NeurIPS 2023 · 39 citations
- An Efficient End-to-End Training Approach for Zero-Shot Human-AI CoordinationAuthor 6 of 6NeurIPS 2023 · 37 citations
- Interpretable Reward Redistribution in Reinforcement Learning: A Causal ApproachAuthor 2 of 7NeurIPS 2023 · 32 citations
- Reduced Policy Optimization for Continuous Control with Hard ConstraintsAuthor 3 of 4NeurIPS 2023 · 10 citations
- Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RLAuthor 6 of 9ICLR 2022 · 100 citations
- Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement LearningAuthor 3 of 4NeurIPS 2022 · 72 citations
- Perceiving the World: Question-guided Reinforcement Learning for Text-based GamesAuthor 4 of 6ACL 2022 · 22 citations
- Generalization in Text-based Games via Hierarchical Reinforcement LearningAuthor 4 of 5EMNLP Findings 2021 · 13 citations
