Reinforcement Learning
Self-Guiding Exploration for Combinatorial Problems
They utilize prompting techniques such as Exploration-of-Thought, Decomposition, and Refinement to effectively navigate and solve intricate tasks.
Regularized Q-Learning
Q-learning is widely used algorithm in reinforcement learning (RL) community. Under the lookup table setting, its convergence is well established.
Shared Autonomy with IDA: Interventional Diffusion Assistance Brandon J. McMahan
The rapid development of artificial intelligence (AI) has unearthed the potential to assist humans in controlling advanced technologies.
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions
Mobile health leverages personalized and contextually tailored interventions optimized through bandit and reinforcement learning algorithms.
Parseval Regularization for Continual Reinforcement Learning
We show that it provides significant benefits to RL agents on a suite of gridworld, CARL and MetaWorld tasks.
Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
To address this, we introduce a conservative fine-tuning approach, BRAID, by optimizing a conservative reward model, which includes additional penalization outside of offline data distributions.
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
These advancements have been enabled in part by the availability of benchmarks.
Hierarchical Programmatic Option Framework Y u-An Lin Chen-T ao Lee Chih-Han Y ang Guan-Ting Liu
However, approximating policies using deep neural networks makes it difficult to interpret the learned decision-making process.