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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “FrozenLake”

Evolution of Q Values for Deep Q Learning in Stable Baselinescs.LG

Investigates Q value evolution in Stable Baselines for DQL in simple vs complex environments.

problem DQL in Stable Baselines struggles with simple non-game environments.

method Comparison of TrafficLight and FrozenLake environments; Q value decomposition analysis.

result Q values meander far from optimal in complex relationships between states.

Deep Q Learning Stable Baselines Q value evolution Reinforcement Learning TrafficLight

2020-04-24abs ↗pdf ↗

Bootstrapping a DQN Replay Memory with Synthetic Experiencescs.LG

Algorithm creates synthetic experiences to enhance Deep Reinforcement Learning.

problem Lack of synthetic experiences in classic Experience Replay.

method Bootstraps synthetic experiences to augment the replay memory.

result Synthetic experiences can improve learning speed and performance.

Reinforcement Learning Experience Replay Synthetic Data Deep Learning FrozenLake

2020-02-04abs ↗pdf ↗

Accelerated Target Updates for Q-learningcs.LG

This paper studies accelerations in Q-learning algorithms. We propose an accelerated target update scheme by incorporating the historical iterates of Q functions. The idea is conceptually inspired by the momentum-based accelerated methods in the optimization theory. Conditions under which the proposed accelerated algor…

2019-05-07abs ↗pdf ↗

Asymptotic Analysis of Sample-averaged Q-learningcs.LG

This paper introduces sample-averaged Q-learning for better RL performance.

problem Improving reinforcement learning algorithms by managing uncertainty.

method Integrates statistical inference into Q-learning through sample averaging and functional central limit theorem.

result Establishes a unified theoretical foundation for sample-averaged Q-learning.

reinforcement learning Q-learning statistical inference functional central limit theorem batch scheduling

2024-10-14abs ↗pdf ↗

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholdingcs.LG

New RL method learns K-step lookahead Q-functions for fixed-horizon MDPs.

problem Challenges in online reinforcement learning for non-episodic, finite-horizon MDPs.

method Introduces a K-step lookahead Q-function with a time-varying threshold for selecting actions.

result Achieves minimax optimal constant regret for K=1 and

\mathcal{O}(\max((K-1),C_{K-1})\sqrt{SAT\log(T)})

regret for K ≥ 2.

reinforcement learning finite horizon lookahead Q-function thresholding tabular learning

2026-01-31abs ↗pdf ↗