10 papers
Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
Yanze Jiang, Mingxuan Li, Yuhao Wang +2
LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents operate over longer horizons…
Counterfactual Shapley Credit Assignment
Mingxuan Li, Kai-Zhan Lee, Elias Bareinboim
The Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents. Existing frameworks, whether relying on temporal cont…
Scalable Causal Imitation Learning
Eylam Tagor, Mingxuan Li, Elias Bareinboim
Imitation learning enables learning a policy in an unknown environment with a latent reward signal using expert demonstrations, but it struggles when the imitator's and expert's ob…
BCTuner: LLM-Guided Monte Carlo Tree Search for Efficient Blockchain Knob Tuning
Yaoyi Deng, Chongyang Tao, Mingxuan Li +4
Knob tuning plays a critical role in improving the performance of permissioned blockchains. However, efficient tuning remains challenging due to the architectural complexity of blo…
Confounding Robust Continuous Control via Automatic Reward Shaping
Mateo Juliani, Mingxuan Li, Elias Bareinboim
Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents' training. However, a principled way of designing effective reward shaping functions, especi…
Causal Flow Q-Learning for Robust Offline Reinforcement Learning
Mingxuan Li, Junzhe Zhang, Elias Bareinboim
Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions fr…
Confounding Robust Deep Reinforcement Learning: A Causal Approach
Mingxuan Li, Junzhe Zhang, Elias Bareinboim
A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, l…
Automatic Reward Shaping from Confounded Offline Data
Mingxuan Li, Junzhe Zhang, Elias Bareinboim
A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, l…
Causally Aligned Curriculum Learning
Mingxuan Li, Junzhe Zhang, Elias Bareinboim
A pervasive challenge in Reinforcement Learning (RL) is the "curse of dimensionality" which is the exponential growth in the state-action space when optimizing a high-dimensional t…
Measuring Fairness in Financial Transaction Machine Learning Models
Deniz Sezin Ayvaz, Lorenzo Belenguer, Hankun He +12
Mastercard, a global leader in financial services, develops and deploys machine learning models aimed at optimizing card usage and preventing attrition through advanced predictive…