A Brief Survey of Deep Reinforcement Learning

Abstract

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep $Q$-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.

arXiv commentIEEE Signal Processing Magazine, Special Issue on Deep Learning for Image Understanding (arXiv extended version)

References in corpus (60)

• Auto-Encoding Variational Bayes
• Distilling the Knowledge in a Neural Network
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Neural Architecture Search with Reinforcement Learning
• Trust Region Policy Optimization
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Prioritized Experience Replay
• Dueling Network Architectures for Deep Reinforcement Learning
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• End-to-End Training of Deep Visuomotor Policies
• Progressive Neural Networks
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Benchmarking Deep Reinforcement Learning for Continuous Control
• Sequence Level Training with Recurrent Neural Networks
• Deep Recurrent Q-Learning for Partially Observable MDPs
• StarCraft II: A New Challenge for Reinforcement Learning
• Emergence of Locomotion Behaviours in Rich Environments
• OpenAI Gym
• Deep Reinforcement Learning: An Overview
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• VIME: Variational Information Maximizing Exploration
• Deep Exploration via Bootstrapped DQN
• Action-Conditional Video Prediction using Deep Networks in Atari Games
• Massively Parallel Methods for Deep Reinforcement Learning
• Learning to Navigate in Complex Environments
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• Continuous Deep Q-Learning with Model-based Acceleration
• Path integrals and symmetry breaking for optimal control theory
• Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
• Maximum Entropy Deep Inverse Reinforcement Learning
• Multi-agent Reinforcement Learning in Sequential Social Dilemmas
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Deep Reinforcement Learning in Large Discrete Action Spaces
• Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
• Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
• FeUdal Networks for Hierarchical Reinforcement Learning
• Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
• Bridging the Gap Between Value and Policy Based Reinforcement Learning
• Memory-based control with recurrent neural networks
• Equivalence Between Policy Gradients and Soft Q-Learning
• Distral: Robust Multitask Reinforcement Learning
• Gradient Estimation Using Stochastic Computation Graphs
• Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
• Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
• Third-Person Imitation Learning
• Towards Deep Symbolic Reinforcement Learning
• Recurrent Environment Simulators
• Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
• Deep Attention Recurrent Q-Network
• Deep Successor Reinforcement Learning
• TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
• Strategic Attentive Writer for Learning Macro-Actions
• Learning model-based planning from scratch
• Discrete Sequential Prediction of Continuous Actions for Deep RL
• Learning to Perform Physics Experiments via Deep Reinforcement Learning
• Recurrent Reinforcement Learning: A Hybrid Approach
• DeepMind Lab
• Model-based Adversarial Imitation Learning
• Classifying Options for Deep Reinforcement Learning

Cited by in corpus (263)

• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• An Introduction to Deep Reinforcement Learning
• Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
• Social physics
• Deep Reinforcement Learning for Cyber Security
• Exploration in Deep Reinforcement Learning: A Survey
• Towards Massive Machine Type Communications in Ultra-Dense Cellular IoT Networks: Current Issues and Machine Learning-Assisted Solutions
• IoT Connectivity Technologies and Applications: A Survey
• A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems
• Medical Deep Learning -- A systematic Meta-Review
• Learning an Approximate Model Predictive Controller with Guarantees
• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• An Application of Deep Reinforcement Learning to Algorithmic Trading
• Bao: Learning to Steer Query Optimizers
• Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach
• Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
• Privacy-Preserved Task Offloading in Mobile Blockchain with Deep Reinforcement Learning
• Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking
• Machine Learning for Intelligent Optical Networks: A Comprehensive Survey
• Artificial Intelligence Enabled Software Defined Networking: A Comprehensive Overview
• AI-enabled Future Wireless Networks: Challenges, Opportunities and Open Issues
• A Survey of Deep Reinforcement Learning in Video Games
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Deep Reinforcement Learning Control for Radar Detection and Tracking in Congested Spectral Environments
• A Review on Computational Intelligence Techniques in Cloud and Edge Computing
• Federated Multi-Agent Actor-Critic Learning for Age Sensitive Mobile Edge Computing
• Video-to-Video Synthesis
• Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
• Assessing Generalization in Deep Reinforcement Learning
• Review: Deep Learning in Electron Microscopy
• Deep Learning for Android Malware Defenses: a Systematic Literature Review
• Blockchain-based Recommender Systems: Applications, Challenges and Future Opportunities
• A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysis
• Intelligent problem-solving as integrated hierarchical reinforcement learning
• An overview of deep learning techniques for epileptic seizures detection and prediction based on neuroimaging modalities: Methods, challenges, and future works
• Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions
• A Survey on Reinforcement Learning for Recommender Systems
• Multi-UAV Path Learning for Age and Power Optimization in IoT with UAV Battery Recharge
• Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks
• Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey
• DRLinFluids -- An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM
• Improving Short Text Classification With Augmented Data Using GPT-3
• Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
• A Review of Safe Reinforcement Learning Methods for Modern Power Systems
• A Deep Reinforcement Learning Approach for the Meal Delivery Problem
• Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
• A Comprehensive Survey of Incentive Mechanism for Federated Learning
• From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: simulations and experiments
• Adaptive Control of Resource Flow to Optimize Construction Work and Cash Flow via Online Deep Reinforcement Learning
• Deep Reinforcement Learning Algorithm for Dynamic Pricing of Express Lanes with Multiple Access Locations
• Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions
• Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding
• Deep Reinforcement Learning for Cybersecurity Threat Detection and Protection: A Review
• The NetHack Learning Environment
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Machine learning \& artificial intelligence in the quantum domain
• Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox
• Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number
• Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation
• Artificial Intelligence for Quantum Computing
• A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art
• DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning
• Tactile based Intelligence Touch Technology in IoT configured WCN in B5G/6G-A Survey
• ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation
• Artificial Intelligence in the Autonomous Navigation of Endovascular Interventions: A Systematic Review
• Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
• Multi-Access Point Coordination for Next-Gen Wi-Fi Networks Aided by Deep Reinforcement Learning
• RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm
• From Screens to Scenes: A Survey of Embodied AI in Healthcare
• Multi-fidelity reinforcement learning framework for shape optimization
• AI in Human-computer Gaming: Techniques, Challenges and Opportunities
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• Quantum Deep Hedging
• Finding Competitive Network Architectures Within a Day Using UCT
• Optimal active particle navigation meets machine learning
• Reinforcement learning for suppression of collective activity in oscillatory ensembles
• FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks
• ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
• Recent Advances in Deep Learning for Channel Coding: A Survey
• A Survey on Resource Allocation in Vehicular Networks
• Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching
• Machine Learning and Quantum Devices
• Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities
• Communication-Efficient Edge AI: Algorithms and Systems
• Deep reinforcement learning in World-Earth system models to discover sustainable management strategies
• Enhancing Efficiency and Propulsion in Bio-mimetic Robotic Fish through End-to-End Deep Reinforcement Learning
• When Cyber-Physical Systems Meet AI: A Benchmark, an Evaluation, and a Way Forward
• Controllable Data Generation by Deep Learning: A Review
• An Empirical Analysis of Deep Learning for Cardinality Estimation
• Reinforcement learning for traversing chemical structure space: Optimizing transition states and minimum energy paths of molecules
• A Scoping Review of Energy-Efficient Driving Behaviors and Applied State-of-the-Art AI Methods
• Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation
• A Memetic Algorithm with Reinforcement Learning for Sociotechnical Production Scheduling
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Deep Active Inference for Partially Observable MDPs
• Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains
• A Survey on Reinforcement Learning for Combinatorial Optimization
• Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search
• A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions
• Differential Mapping Spiking Neural Network for Sensor-Based Robot Control
• A Learning-Based Trajectory Planning of Multiple UAVs for AoI Minimization in IoT Networks
• Deep Learning for Insider Threat Detection: Review, Challenges and Opportunities
• Physical Layer Security for Integrated Sensing and Communication: A Survey
• Specification Overfitting in Artificial Intelligence
• Deep Learning in Mining Biological Data
• Deep reinforcement learning for key distribution based on quantum repeaters
• Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization
• Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach
• The Wireless Control Plane: An Overview and Directions for Future Research
• Balancing a CartPole System with Reinforcement Learning -- A Tutorial
• Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement Learning
• Specialization in Hierarchical Learning Systems
• A Deep Model for Partial Multi-Label Image Classification with Curriculum Based Disambiguation
• A Survey of Reinforcement Learning for Optimization in Automation
• Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation
• Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey
• Model-Aided Wireless Artificial Intelligence: Embedding Expert Knowledge in Deep Neural Networks Towards Wireless Systems Optimization
• Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data
• Parallel Exploration via Negatively Correlated Search
• Falsification-Based Robust Adversarial Reinforcement Learning
• Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges
• Monte Carlo Tree Search with Spectral Expansion for Planning with Dynamical Systems
• Experimental Analysis of Reinforcement Learning Techniques for Spectrum Sharing Radar
• Variable impedance control and learning -- A review
• Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator
• A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search
• Bayesian Optimization Meets Riemannian Manifolds in Robot Learning
• Low Precision Decentralized Distributed Training over IID and non-IID Data
• Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
• Student-Initiated Action Advising via Advice Novelty
• Scalable Imaginary Time Evolution with Neural Network Quantum States
• Deep Reinforcement Learning Based High-level Driving Behavior Decision-making Model in Heterogeneous Traffic
• SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents
• A Survey of Behavior Learning Applications in Robotics -- State of the Art and Perspectives
• Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies
• Transformer Based Reinforcement Learning For Games
• Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in Sepsis Patients
• Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
• Explainable Artificial Intelligence (XAI) for 6G: Improving Trust between Human and Machine
• Deep Actor-Critic Learning for Distributed Power Control in Wireless Mobile Networks
• A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures
• Energy-Efficient and Intelligent ISAC in V2X Networks with Spiking Neural Networks-Driven DRL
• Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agent
• Symbolic Equation Solving via Reinforcement Learning
• Integration of Reinforcement Learning Based Behavior Planning With Sampling Based Motion Planning for Automated Driving
• Deep Learning in Physical Layer Communications
• A Reinforcement Learning Approach for an IRS-assisted NOMA Network
• Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
• Deep Reinforcement Learning for the Heat Transfer Control of Pulsating Impinging Jets
• Increasing performance of electric vehicles in ride-hailing services using deep reinforcement learning
• Optimizing Deep Reinforcement Learning for Adaptive Robotic Arm Control
• Entanglement engineering of optomechanical systems by reinforcement learning
• Discovering Efficient Periodic Behaviours in Mechanical Systems via Neural Approximators
• Adaptive Control Strategy for Quadruped Robots in Actuator Degradation Scenarios
• Investigation of reinforcement learning for shape optimization of profile extrusion dies
• Solving the scalarization issues of Advantage-based Reinforcement Learning Algorithms
• Graph Reinforcement Learning for Power Grids: A Comprehensive Survey
• Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL
• Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning
• Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement
• HyperNCA: Growing Developmental Networks with Neural Cellular Automata
• Attacking Black-box Recommendations via Copying Cross-domain User Profiles
• Parametric-Task MAP-Elites
• Adaptive Road Configurations for Improved Autonomous Vehicle-Pedestrian Interactions using Reinforcement Learning
• Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction
• Deep Reinforcement Learning for Active High Frequency Trading
• Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation
• An Invitation to Deep Reinforcement Learning
• A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation
• Zeroth-order Deterministic Policy Gradient
• Hierarchical principles of embodied reinforcement learning: A review
• Safer Deep RL with Shallow MCTS: A Case Study in Pommerman
• Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression and Challenge
• Computational Rational Engineering and Development: Synergies and Opportunities
• Independent Natural Policy Gradient Always Converges in Markov Potential Games
• Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning
• Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments
• Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning?
• UAV-to-Device Underlay Communications: Age of Information Minimization by Multi-agent Deep Reinforcement Learning
• Quantum Circuit Distillation and Compression
• Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator
• OpenFed: A Comprehensive and Versatile Open-Source Federated Learning Framework
• Neural Policy Style Transfer
• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
• Indoor thermal comfort management: A Bayesian machine-learning approach to data denoising and dynamics prediction of HVAC systems
• Proportional integral derivative controller assisted reinforcement learning for path following by autonomous underwater vehicles
• Stigmergic Independent Reinforcement Learning for Multi-Agent Collaboration
• Reinforcement learning reward function in unmanned aerial vehicle control tasks
• Hierarchical Expert Networks for Meta-Learning
• A Mapping of Assurance Techniques for Learning Enabled Autonomous Systems to the Systems Engineering Lifecycle
• Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space
• Reinforcement Learning in Non-Markov Market-Making
• An Energy and Carbon Footprint Analysis of Distributed and Federated Learning
• Kernel-based diffusion approximated Markov decision processes for autonomous navigation and control on unstructured terrains
• Program Synthesis Guided Reinforcement Learning for Partially Observed Environments
• Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
• Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
• Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey
• Information-theoretic convergence of extreme values to the Gumbel distribution
• Learning to be Global Optimizer
• Reinforcement Learning for a Cellular Internet of UAVs: Protocol Design, Trajectory Control, and Resource Management
• Enhancing MAP-Elites with Multiple Parallel Evolution Strategies
• Sample-Efficient Reinforcement Learning with Maximum Entropy Mellowmax Episodic Control
• Learning a generative model for robot control using visual feedback
• Learning Knowledge Graph-based World Models of Textual Environments
• Reinforcing Medical Image Classifier to Improve Generalization on Small Datasets
• Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
• Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments
• RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN
• MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl
• Energy-Efficient Design for a NOMA assisted STAR-RIS Network with Deep Reinforcement Learning
• Explainable Deep Reinforcement Learning Using Introspection in a Non-episodic Task
• Active Screening for Recurrent Diseases: A Reinforcement Learning Approach
• Intelligent Network Slicing for V2X Services Towards 5G
• Approximation of Optimal Control Surfaces for $2\times 2$ Skew-Symmetric Evolutionary Game Dynamics
• Model-Free Design of Stochastic LQR Controller from Reinforcement Learning and Primal-Dual Optimization Perspective
• A New Approach for Tactical Decision Making in Lane Changing: Sample Efficient Deep Q Learning with a Safety Feedback Reward
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact
• A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning
• Autonomous UAV Base Stations for Next Generation Wireless Networks: A Deep Learning Approach
• Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation
• Modeling Worlds in Text
• Convolutional Reservoir Computing for World Models
• Reinforcement Learning with Convolutional Reservoir Computing
• On Hyper-parameter Tuning for Stochastic Optimization Algorithms
• Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models
• Learn Task First or Learn Human Partner First: A Hierarchical Task Decomposition Method for Human-Robot Cooperation
• UAV Communications Based on Non-Orthogonal Multiple Access
• Learning optimal policies from event logs through reinforcement learning: a comparison of deep and MDP-based approaches
• Flexible and Efficient Long-Range Planning Through Curious Exploration
• Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games
• Episodic Self-Imitation Learning with Hindsight
• Learning to Grasp from 2.5D images: a Deep Reinforcement Learning Approach
• Cellular UAV-to-Device Communications: Trajectory Design and Mode Selection by Multi-agent Deep Reinforcement Learning
• Communication-Computation Efficient Device-Edge Co-Inference via AutoML
• SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning
• Reinforcement Learning Architectures: SAC, TAC, and ESAC
• Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations
• BF++: a language for general-purpose program synthesis
• Interpretable UAV Collision Avoidance using Deep Reinforcement Learning
• Thompson Sampling via Local Uncertainty
• On Deep Learning for Radio Resource Management in A Non-stationary Radio Environment
• Techniques Toward Optimizing Viewability in RTB Ad Campaigns Using Reinforcement Learning
• Decentralized Deep Reinforcement Learning for Network Level Traffic Signal Control
• The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication
• RLCache: Automated Cache Management Using Reinforcement Learning
• Generalized Operating Procedure for Deep Learning: an Unconstrained Optimal Design Perspective
• Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders
• Constrained Policy Gradient Method for Safe and Fast Reinforcement Learning: a Neural Tangent Kernel Based Approach
• Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
• Optimal control of batch processes via a deterministic Q-learning method
• MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management
• DeepAir: A Multi-Agent Deep Reinforcement Learning Based Scheme for an Unknown User Location Problem
• Augmenting PID Control with Deep Reinforcement Learning: A Hybrid Approach to the Industrial Benchmark
• Curriculum-based Sensing Reduction in Simulation to Real-World Transfer for In-hand Manipulation
• Algebras of actions in an agent's representations of the world
• Partially Observable Planning and Learning for Systems with Non-Uniform Dynamics
• Continuous Deep Q-Learning with Simulator for Stabilization of Uncertain Discrete-Time Systems