sequential decision-making
Sequential decision-making refers to scenarios where decisions are made in a sequence, with each decision potentially affecting future options and outcomes. This is critical in fields like reinforcement learning and planning.
- Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing
- Adaptive Variance Inflation in Thompson Sampling: Efficiency, Safety, Robustness, and Beyond
- Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation
- AutoEdit: Automatic Hyperparameter Tuning for Image Editing
- Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework
- DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
- Emergent Risk Awareness in Rational Agents under Resource Constraints
- Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
- Markov Persuasion Processes: Learning to Persuade From Scratch
- Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
- No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
- Non-Stationary Structural Causal Bandits
- On Evaluating Policies for Robust POMDPs
- Prediction with expert advice under additive noise
- RF-Agent: Automated Reward Function Design via Language Agent Tree Search
- Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks
- What do you know? Bayesian knowledge inference for navigating agents