#DeepReinforcementLearning
LightNews LightNews
ezgikorkmaz.bsky.social
I wrote a recent survey about deep reinforcement learning. The paper is a compact guide to understand some of the key concepts in reinforcement learning.

Link: arxiv.org/pdf/2401.023...

#ReinforcementLearning #ICLR2025 #ACL2025 #NAACL2025 #NeurIPS2024 #ICML2025 #DeepRL #DeepReinforcementLearning
January 12, 2025 at 4:21 PM
ezgikorkmaz.bsky.social
A recent paper I wrote introduces foundational analysis on deep reinforcement learning decision making and representations learnt by it.

Link: proceedings.mlr.press/v235/korkmaz...

#ReinforcementLearning #ICLR2025 #ACL2025 #NAACL2025 #NeurIPS2024 #ICML2025 #DeepRL #DeepReinforcementLearning
January 14, 2025 at 2:15 PM
hackernoon.com
IA2 uses Deep Reinforcement Learning to slash database runtimes by 40%, while new Hyperbolic SVM techniques utilize semidefinite relaxation. #deepreinforcementlearning
AI-Driven Database Tuning: Faster Index Selection with IA2 and TD3-TD-SWAR
hackernoon.com
January 13, 2026 at 2:12 AM
ezgikorkmaz.bsky.social
If you are interested in deep reinforcement learning, I will share this repo here:

Link: github.com/EzgiKorkmaz/...

#ReinforcementLearning #SafeAI #Adversarial #Robust #DeepRL #robustRL #LanguageModels #AdversarialRL #AISafety #ExplainableAI #TrustworthyAI #ResponsibleAI #DeepReinforcementLearning
GitHub - EzgiKorkmaz/adversarial-reinforcement-learning: Reading list for adversarial perspective and robustness in deep reinforcement learning.
Reading list for adversarial perspective and robustness in deep reinforcement learning. - EzgiKorkmaz/adversarial-reinforcement-learning
github.com
January 22, 2025 at 3:59 PM
duckietown.bsky.social
Deep reinforcement and transfer learning for autonomous robots, how does it work? 🤔

Find out more: t.co/x42FlhLm8e

🤖 Get your Duckiebot and Duckiedrone - t.co/p6XbHk78wr

#Robotics #AI #DeepReinforcementLearning #TransferLearning #Sim2Real t.co/kKW3qLURNX
March 14, 2025 at 1:43 PM
ezgikorkmaz.bsky.social
If you are interested in large language models see my paper below on how we can uncover the biases learned by these models.

Link: neurips2023-enlsp.github.io/papers/paper...

#ReinforcementLearning #FoundationModels #DeepRL #DeepReinforcementLearning #ResponsibleAI #AIBias #LLMs #LanguageModels
February 11, 2025 at 5:56 PM
ezgikorkmaz.bsky.social
The recent paper I wrote on deep reinforcement learning and generalization will appear #NeurIPS2024 @neuripsconf.bsky.social !

#ReinforcementLearning #DeepReinforcementLearning
December 10, 2024 at 6:35 PM
proceedingsieee.bsky.social
Explore our June issue for insights into #deeplearning methods for #superresolution, the application of #deepreinforcementlearning in #powersystems, and #analogtodigitalconverters for #IoT.

Read more: bit.ly/42UGYBr
October 22, 2025 at 3:59 AM
pneumetron.bsky.social
New Research Challenges Canonical Deep Reinforcement Learning Evaluation Paradigms

https://pneumetron.com/news/ai_research/new-research-challenges-canonical-deep-reinforcement-learning-evaluation-paradigms-4a556c

#DeepReinforcementLearning #DRL #EvaluationParadigms #Scalin
July 15, 2026 at 3:57 PM
annabel-baker.bsky.social
Process Optimization Cuts Inventory Costs 15% Instantly

https://opssuite.site/process-optimization-cuts-inventory-costs-15-perce/?utm_source=bluesky&utm_medium=social
#deepreinforcementlearning #inventoryreplenishment #erpoptimization
August 20, 2026 at 2:40 AM
getnews-me.bsky.social
Deep reinforcement learning achieved up to 95% vibration reduction of a circular cylinder in a water‑tunnel flow at Reynolds ≈3000, even with actuator delay. Read more: https://getnews.me/deep-rl-controls-vortex-induced-vibrations-in-real-time/ #deepreinforcementlearning #fluidcontrol
Deep RL Controls Vortex‑Induced Vibrations in Real Time
September 30, 2025 at 10:05 PM
acsacconf.bsky.social
Last but not least, came Tekgul & Asokan's "FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks" which is robust to model modification attacks. (www.acsac.org/2023/p...) 4/4
#MachineLearningSecurity #DeepReinforcementLearning #SecurityInAI
Tekgul & Asokan's "FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks"
June 20, 2024 at 2:01 PM
hackernoon.com
IA2 revolutionizes index selection with rapid training, reducing SQL runtime by 61% via adaptive action pruning and workload modeling #deepreinforcementlearning
Adaptive Action Pruning: Scaling Index Selection for Unseen Workloads
hackernoon.com
January 10, 2026 at 2:26 AM
hackernoon.com
IA2 uses a two-phase framework to generate states and action pools from workloads, enabling RL agents to make sequential index selection decisions. #deepreinforcementlearning
Unseen Workload Optimization: The Two-Phase IA2 Approach
hackernoon.com
January 6, 2026 at 2:45 AM
hackernoon.com
The TD3-TD-SWAR model advances database optimization by framing index selection as a DRL problem with adaptive action masking for faster training. #deepreinforcementlearning
Adaptive Action Masking: Accelerating Decision-Making in Database Tuning
hackernoon.com
December 24, 2025 at 2:18 AM
hackernoon.com
IA2 uses the TD3-TD-SWAR model and DRL to optimize index selection, reducing TPC-H workload runtime by 40% via adaptive action masking. #deepreinforcementlearning
Reducing TPC-H Workload Runtime by 40% with IA2 Deep Reinforcement Learning
hackernoon.com
December 23, 2025 at 3:15 PM
hackernoon.com
This research validates a weekly re-trained DRL agent, showing it outperforms static models & Black-Scholes for practical American option hedging. #deepreinforcementlearning
Validating Hyperparameters and a Weekly Re-training Strategy for DRL Option Hedging
hackernoon.com
August 26, 2025 at 10:00 AM
hackernoon.com
This methodology details how to train and test DRL agents for American option hedging, introducing a novel weekly re-training strategy using Chebyshev pricing. #deepreinforcementlearning
Don't Just Train Your AI, Re-Train It: The Weekly Workout Plan for a Smarter Option Hedge
hackernoon.com
August 26, 2025 at 9:51 AM
hackernoon.com
This review of DRL hedging literature highlights the need for hyperparameter analysis, especially for real-world American option applications. #deepreinforcementlearning
Avoiding the Pitfalls: A Guide to the Current State of DRL Option Hedging Research
hackernoon.com
August 26, 2025 at 9:39 AM
hackernoon.com
This paper makes Deep Reinforcement Learning practical for hedging American options by optimizing hyperparameters and using a weekly re-training strategy. #deepreinforcementlearning
How Weekly AI Training Is Beating a Nobel Prize-Winning Formula
hackernoon.com
August 26, 2025 at 9:35 AM
aiadoptionagency.bsky.social
Generative AI Glossary – Part 16

As artificial intelligence continues to transform industries and reshape how we approach complex....

#GenerativeAI #AIGlossary #AttentionMechanisms #BehavioralCloning #DeepReinforcementLearning #AITech

Read more:

aiadoptionagency.com/generative-a...
Generative AI Glossary – Part 16 - Ai Adoption Agency
As artificial intelligence continues to transform industries and reshape how we approach complex problems, it is essential to expand our understanding of its underlying concepts. This sixteenth instal...
https://aiadoptionagency.com/generative-ai-glossary-part-16/"
March 3, 2025 at 7:11 PM
informaq.bsky.social
A DDQN framework autonomously designs VITE quantum circuits with 37% fewer gates & 43% less depth for Max-Cut, and reaches Full-CI accuracy for H₂ with shallower circuits — though scaling to complex molecules remains an open challenge.

#QuantumCircuits #DeepReinforcementLearning #News
AI-Designed Quantum Circuits Achieve 37% Gate Reduction via Deep Reinforcement Learning
iq.fp2.dev
April 13, 2026 at 9:41 PM
eshmunai.bsky.social
Every 1% efficiency gain in wind = $200K/year/100MW.
9-month payback.

88% of AI energy research never leaves the lab.

New essay on why Deep RL is finally bridging the deployment gap—impact on $50-100B AI energy market.

Full analysis ⬇️
buff.ly/bDPhBjT

#AI #ClimateTech #DeepReinforcementLearning
Deep reinforcement learning is transforming wind energy economics at scale
Artificial intelligence is delivering 1-20% efficiency improvements in wind farm operations through software-only implementations.
open.substack.com
October 3, 2025 at 2:45 PM
proceedingsieee.bsky.social
#Deepreinforcementlearning (DRL) shows great promise in managing the complexity of the modern electric #powerdistributionsystems. This tutorial outlines how to translate operational tasks into #Markovdecisionprocess formulations suitable for DRL implementation. bit.ly/47FvX8w
November 11, 2025 at 3:01 AM
arxivlens.bsky.social
Safe Obstacle-Free Guidance of Space Manipulators in Debris Removal
Missions via Deep Reinforcement Learning
Robin Chhabra, Vincent Lam
Paper
Details
#SpaceDebrisRemoval #DeepReinforcementLearning #RoboticsInSpace
October 10, 2025 at 4:02 PM