Deep Reinforcement Learning
Deep reinforcement learning (DRL) aims to train agents to make optimal decisions in complex environments by learning through trial and error. Current research focuses on improving DRL's robustness, sample efficiency, and interpretability, often employing architectures like Proximal Policy Optimization (PPO), deep Q-networks (DQNs), and graph neural networks (GNNs) to address challenges in diverse applications such as robotics, game playing, and resource management. The resulting advancements have significant implications for various fields, enabling the development of more adaptable and efficient autonomous systems across numerous domains.
1498papers
Papers - Page 30
February 8, 2024
February 7, 2024
Analyzing Adversarial Inputs in Deep Reinforcement Learning
A computational approach to visual ecology with deep reinforcement learning
Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigation
Exploration Without Maps via Zero-Shot Out-of-Distribution Deep Reinforcement Learning
Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning
Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving
A Deep Reinforcement Learning Approach for Adaptive Traffic Routing in Next-gen Networks
February 5, 2024
February 4, 2024
February 1, 2024
Neural Policy Style Transfer
Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management
RadDQN: a Deep Q Learning-based Architecture for Finding Time-efficient Minimum Radiation Exposure Pathway
AlphaRank: An Artificial Intelligence Approach for Ranking and Selection Problems