Deep Q-Network
PulseAugur coverage of Deep Q-Network — every cluster mentioning Deep Q-Network across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New algorithm CDE tackles stability-plasticity dilemma in adaptive train scheduling
Researchers have developed a new algorithm called Continual Deep Q-Network Expansion (CDE) to address the stability-plasticity dilemma in adaptive train scheduling. This problem involves balancing the preservation of pr…
-
Reinforcement learning models show promise for adaptive chemotherapy control
Researchers have developed and compared closed-loop deep reinforcement learning (DRL) policies for adaptive chemotherapy control, utilizing both continuous (TD3) and discrete (DQN) action spaces. These DRL policies were…
-
Six techniques enhance Deep Q-Network agents, with Java implementations
Guilherme Alves Silveira has detailed six techniques that can enhance the capabilities of a Deep Q-Network (DQN) agent. The focus is on understanding the specific improvements each technique offers, rather than just the…
-
New framework enhances robotic control over unreliable wireless networks
Researchers have developed a new framework for resilient remote robotic control over wireless networks. This approach couples control systems with Joint Embedding Predictive Architecture (JEPA) world models to jointly l…
-
New LUGL framework enables gradient-boosted trees for RL game-playing
Researchers have developed a new framework called LUGL (Local Updates, Global Learning) that allows non-incremental learners, such as gradient-boosted trees (GBTs), to be effectively used in reinforcement learning (RL) …
-
New LUGL framework enables gradient-boosted trees for reinforcement learning games
Researchers have developed a new framework called LUGL (Local Updates, Global Learning) that allows non-incremental learners, such as gradient-boosted trees (GBTs), to be effective in reinforcement learning (RL) setting…
-
Reinforcement learning and rule-based pricing compared for P2P electricity trading
This paper explores two pricing mechanisms for peer-to-peer electricity trading in residential photovoltaic communities: rule-based and reinforcement learning (RL) based. The rule-based methods include bill-sharing, mid…
-
New hierarchical RL framework enhances conversational agents
Researchers have developed a novel two-level hierarchical reinforcement learning (RL) framework called ToSCA for conversational agents. This approach bridges the gap between existing token-level or utterance-level RL me…
-
New L4V method optimizes AAV trajectories for IoT data collection
Researchers have developed a new method called Learn for Variation (L4V) to optimize the trajectories of autonomous aerial vehicles (AAVs) for data collection in sixth-generation Internet of Things networks. L4V utilize…
-
New multi-agent DRL framework optimizes base station placement
Researchers have developed a new multi-agent deep reinforcement learning framework to optimize the placement of millimeter-wave base stations in complex campus environments. The study benchmarks four deep reinforcement …
-
LLM-enhanced traffic control system SIGMA reduces delays
Researchers have developed SIGMA, a novel reinforcement learning framework for traffic signal control that incorporates a large language model (LLM) for adaptive objective tuning. This system can interpret natural-langu…
-
Robotic grasping improved with deep reinforcement learning
Researchers have developed a novel reinforcement learning framework to improve robotic grasping capabilities. This system integrates a Deep Q-Network (DQN) with keypoint-based object representations, using 2D images to …
-
Deep Reinforcement Learning Optimizes Smart Factory Scheduling with RFID Data
This paper introduces a novel dynamic shop floor production scheduling framework for smart factories that utilize RFID technology. The approach addresses uncertainties in manufacturing processes by analyzing RFID-collec…
-
Deep Q-Network enhances cloud cyber defense with 99.72% accuracy
Researchers have developed a novel cybersecurity framework utilizing a Deep Q-Network (DQN) to enhance cloud infrastructure defense against sophisticated cyberattacks. This reinforcement learning-based approach trains a…
-
New AI benchmark environment created for Dark Souls boss fights · 2 sources tracked
Researchers have developed the Dark Souls Learning Environment (DSLE), a platform designed to benchmark AI agents against the boss encounters in Dark Souls: Remastered. The environment presents 22 boss fights as challen…
-
Google DeepMind CEO Demis Hassabis steps down; Koray Kavukcuoglu takes over
Google DeepMind has seen a significant leadership change with CEO Demis Hassabis stepping down to become Chairman and Alphabet Chief Scientist, while Koray Kavukcuoglu takes over as Senior Vice President of Google DeepM…
-
New SADQ method enhances Q-value updates in Deep Q-Learning
Researchers have developed the Successor-state Aggregation Deep Q-Network (SADQ), a novel approach to enhance Q-value updates in Deep Q-Learning (DQN). SADQ addresses the issue of high variance in DQN updates caused by …
-
New reward shaping framework improves autonomous car parking AI
Researchers have developed a new reward shaping framework for reinforcement learning agents, specifically addressing challenges in autonomous vehicle parking under non-holonomic constraints. This framework incorporates …
-
Reinforcement learning accelerates laser design, Dueling DQN shows promise
Researchers have developed a new method using value-based reinforcement learning to accelerate the design of photonic-crystal surface-emitting lasers (PCSELs). In a study with a limited simulation budget of 83 calls, Du…
-
UAV-IRS communications boosted by D3QN-PER for secrecy energy efficiency
Researchers have developed a novel approach to enhance secrecy energy efficiency in low-altitude wireless communications by integrating unmanned aerial vehicles (UAVs) with intelligent reflecting surfaces (IRS). The pro…