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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Q-ensembles”

Combining Model-Free Q-Ensembles and Model-Based Approaches for Informed Explorationcs.LG

Combines model-free Q-ensembles and model-based approaches for improved exploration.

problem Improving exploration strategies in reinforcement learning.

method Integrates model-free Q-ensembles and model-based trajectory memory approaches.

result Model-based trajectory memory combined with Q-ensembles outperforms Q-ensembles alone.

reinforcement learning exploration strategies Q-ensembles model-based trajectory memory

2018-06-12abs ↗pdf ↗

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learningcs.LG

SPQR improves Q-ensemble diversity in reinforcement learning.

problem Overestimation bias in Q-learning for complex tasks.

method Introduces SPQR for Q-ensemble independence regularization.

result SPQR outperforms baseline algorithms in online and offline RL benchmarks.

reinforcement learning Q-learning ensemble methods overestimation bias random matrix theory

2024-01-06abs ↗pdf ↗

UCB Exploration via Q-Ensemblescs.LG

We show how an ensemble of $Q^*$ -functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$ -learning setting. We propose an exploration strategy based on upper-confidence bounds (UCB). Our experimen…

2017-06-05abs ↗pdf ↗

Effective Exploration for Deep Reinforcement Learning via Bootstrapped Q-Ensembles under Tsallis Entropy Regularizationcs.LG

New DRL algorithm improves sample efficiency and exploration performance.

problem High sample cost in deep reinforcement learning.

method Combines entropy and bootstrap techniques with Tsallis entropy regularization.

result Demonstrates more efficient and effective exploration on Atari games.

deep reinforcement learning entropy regularization bootstrapping Tsallis entropy sample efficiency

2018-09-02abs ↗pdf ↗

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learningcs.LG

SUNRISE improves off-policy RL algorithms by integrating ensemble methods.

problem Stability and exploration issues in off-policy RL algorithms.

method SUNRISE combines ensemble-based weighted Bellman backups and upper-confidence bounds for efficient exploration.

result SUNRISE improves the performance of off-policy RL algorithms across various domains.

reinforcement learning ensemble methods off-policy deep learning exploration

2020-07-09abs ↗pdf ↗