On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “Off-Dynamics”

A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learningcs.LG

Proposes a method to improve few-shot transfer in off-dynamics RL.

problem Traditional RL struggles with transferring policies between environments with different dynamics.

method Introduces a penalty to regulate source-trained policies in target environments with limited data.

result Improves performance in various off-dynamics RL scenarios compared to existing methods.

Reinforcement Learning Transfer Learning Few-Shot Learning Off-Dynamics Conservative RL

2023-12-24abs ↗pdf ↗

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learningcs.LG

Enhances RL in target domains with limited data using augmented return.

problem Utilize data from an accessible source domain to improve policy learning in a target domain with scarce data.

method Return Augmented Decision Transformer (REAG) method, which augments the return in the source domain to align with the target domain's optimal trajectory distribution.

result The proposed REAG method achieves the same level of suboptimality as without a dynamics shift, enhancing DT type frameworks' performance in off-dynamics RL.

Reinforcement Learning Decision Transformer Return Augmentation Off-Dynamics Supervised Learning

2024-10-30abs ↗pdf ↗

Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learningcs.LG

We develop a robust RL algorithm for off-dynamics environments with improved suboptimality bounds and computational efficiency.

problem Learning policies robust to uncertainties in transition dynamics between training and deployment environments.

method Distributionally robust Markov decision processes (DRMDPs) with a novel algorithm We-DRIVE-U.

result Improved suboptimality bound of

\widetilde{\mathcal{O}}\big({d H \cdot \min \{1/ρ, H\}/\sqrt{K} }\big)

, near-optimal up to

\mathcal{O}(\sqrt{H})

Reinforcement Learning Distributionally Robust Off-Dynamics Markov Decision Processes Suboptimality Bounds

2024-09-30abs ↗pdf ↗

Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interactioncs.LG

Study online RL with mismatched dynamics, achieving sublinear regret.

problem Exploration challenges in online RL with mismatched training and deployment dynamics.

method Introduce supremal visitation ratio, propose efficient algorithm with

f

-divergence.

result Achieves sublinear regret in online RMDPs with optimal dependence on supremal visitation ratio and interaction episodes.

Reinforcement Learning Distributionally Robust Online Interaction Sublinear Regret Supremal Visitation Ratio

2025-11-07abs ↗pdf ↗

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifierscs.LG

A new method for reinforcement learning that adapts to different domains using auxiliary classifiers.

problem Training reinforcement learning agents to perform well in different domains with varying dynamics.

method Learning auxiliary classifiers to distinguish source-domain from target-domain transitions and modifying the reward function accordingly.

result The approach improves transfer performance in reinforcement learning tasks with varying dynamics.

reinforcement learning domain adaptation auxiliary classifiers reward modification probabilistic view

2020-06-24abs ↗pdf ↗

Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Randomcs.LG

Paper tackles bias-variance trade-off in missing data, proposing a dynamic framework.

problem Missing data in practical applications deteriorates model performance.

method Develops a fine-grained dynamic learning framework to jointly optimize bias and variance.

result Theoretical and empirical validation of joint bias-variance optimization.

missing data bias-variance trade-off dynamic learning generalization bound propensity scores

2024-05-24abs ↗pdf ↗

Recovering lost and absent information in temporal networkscs.SI

Recovering edge activities from node activity data in temporal networks.

problem Recovering lost edge activity data from aggregated node activity data in temporal networks.

method Analyzing the relationship between edge activity and node activity data, using both theoretical and empirical methods to show recovery is possible and under what conditions.

result Recovery of edge activities from node activities is possible with surprising accuracy, even when network density increases.

temporal networks edge activity node activity recovery problem privacy concerns

2021-07-22abs ↗pdf ↗

Linear Mixture Distributionally Robust Markov Decision Processescs.LG

A new framework for robust policy learning in MDPs with linear mixture dynamics.

problem Off-dynamics challenge in real-world decision-making problems.

method Linear mixture DRMDP framework, meta algorithm for robust policy learning.

result The new framework provides a more refined representation of uncertainties.

distributionally robust Markov decision processes linear mixture meta algorithm f-divergence

2025-05-23abs ↗pdf ↗