ASCEND
BY NTHRYS

NTHRYS › PhD Assistance › Reinforcement Learning

Reinforcement Learning

Field
▾
Category
▾

Reinforcement Learning

Select a category to explore research frontiers

Loading categories...

Research Frontiers in Offline Reinforcement Learning Methods

Development of RL algorithms that learn effective policies from fixed, pre-collected datasets without online environment interaction.

Distributional Shift and Extrapolation Boundaries in Offline Learning
Implicit Behavior Regularization Through Pessimistic Value Functions
Multi-Modal Reward Inference From Heterogeneous Offline Data
Uncertainty Quantification in Batch-Constrained Policy Optimization
Latent Dynamics Disentanglement for Offline Model-Based Control
Conservative Exploration in High-Dimensional Action Spaces
Offline-to-Online Bridging: Adaptation Without Environment Resets
Inverse Models as Implicit Behavior Priors in Offline RL
Value Extrapolation and Phantom Actions in Batch Learning
Trajectory Stitching Across Discontinuous Offline Datasets

All Reinforcement Learning PhD categories