Prioritized Experience Replay

Abstract

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.

Published at ICLR 2016

References in corpus (3)

• Massively Parallel Methods for Deep Reinforcement Learning
• No More Pesky Learning Rates
• Planning by Prioritized Sweeping with Small Backups

Cited by in corpus (369)

• A Brief Survey of Deep Reinforcement Learning
• Asynchronous Methods for Deep Reinforcement Learning
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• Applications of Deep Learning and Reinforcement Learning to Biological Data
• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Deep Reinforcement Learning for Cyber Security
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• DeepMind Control Suite
• A Review of Deep Reinforcement Learning for Smart Building Energy Management
• Deep Exploration via Bootstrapped DQN
• PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning
• Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
• Parameter Space Noise for Exploration
• Hindsight Experience Replay
• A Survey of End-to-End Driving: Architectures and Training Methods
• AI based Service Management for 6G Green Communications
• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• An Application of Deep Reinforcement Learning to Algorithmic Trading
• Federated Reinforcement Learning: Techniques, Applications, and Open Challenges
• Go-Explore: a New Approach for Hard-Exploration Problems
• Distral: Robust Multitask Reinforcement Learning
• A Deeper Look at Experience Replay
• Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
• DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning
• Model-Free Episodic Control
• Online Batch Selection for Faster Training of Neural Networks
• Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
• Lyapunov-based Safe Policy Optimization for Continuous Control
• Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized Intersections
• Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review
• A User Simulator for Task-Completion Dialogues
• A Deep Hierarchical Approach to Lifelong Learning in Minecraft
• InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
• Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
• Deep Reinforcement Learning for Quantum Gate Control
• Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving
• Reinforcement Learning in Healthcare: A Survey
• Reinforcement Learning Algorithms: An Overview and Classification
• A review on Deep Reinforcement Learning for Fluid Mechanics
• A review on deep reinforcement learning for fluid mechanics: an update
• Review: Deep Learning in Electron Microscopy
• RUDDER: Return Decomposition for Delayed Rewards
• Not All Samples Are Created Equal: Deep Learning with Importance Sampling
• Optimal Client Sampling for Federated Learning
• Sim-to-Real Reinforcement Learning for Deformable Object Manipulation
• Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
• Neural Episodic Control
• DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction
• A survey on intrinsic motivation in reinforcement learning
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions
• Combining policy gradient and Q-learning
• Deep Successor Reinforcement Learning
• Learning Montezuma's Revenge from a Single Demonstration
• How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies
• A Lyapunov-based Approach to Safe Reinforcement Learning
• Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay
• Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Learning to Continually Learn
• Deep Reinforcement Learning Control of Quantum Cartpoles
• R-MADDPG for Partially Observable Environments and Limited Communication
• Stabilizing Generative Adversarial Networks: A Survey
• Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization
• A Deep Reinforcement Learning Approach for the Meal Delivery Problem
• Adaptive Behavior Generation for Autonomous Driving using Deep Reinforcement Learning with Compact Semantic States
• Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes
• Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
• Inference and dynamic decision-making for deteriorating systems with probabilistic dependencies through Bayesian networks and deep reinforcement learning
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Deep reinforcement learning for guidewire navigation in coronary artery phantom
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning
• First Order Constrained Optimization in Policy Space
• rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
• Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
• Experience-driven Networking: A Deep Reinforcement Learning based Approach
• Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
• Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning
• Playing Doom with SLAM-Augmented Deep Reinforcement Learning
• Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning
• Autonomous Quadrotor Landing using Deep Reinforcement Learning
• CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
• Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past
• ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning
• Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
• Reward learning from human preferences and demonstrations in Atari
• Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
• Learning Permutations with Sinkhorn Policy Gradient
• A Deep Reinforcement Learning-Based Resource Scheduler for Massive MIMO Networks
• Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning
• Memory Based Online Learning of Deep Representations from Video Streams
• Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning
• Parameterized Reinforcement Learning for Optical System Optimization
• Continuous-Time Mean-Variance Portfolio Selection: A Reinforcement Learning Framework
• Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
• Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
• Physical Informed-Inspired Deep Reinforcement Learning Based Bi-Level Programming for Microgrid Scheduling
• Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network
• Deep reinforcement learning in World-Earth system models to discover sustainable management strategies
• Deep Reinforcement Learning Methods for Structure-Guided Processing Path Optimization
• Hierarchical Imitation and Reinforcement Learning
• Network slicing for vehicular communications: a multi-agent deep reinforcement learning approach
• FuzzerGym: A Competitive Framework for Fuzzing and Learning
• Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs
• Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
• Interactive Fiction Games: A Colossal Adventure
• TDM: Trustworthy Decision-Making via Interpretability Enhancement
• Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment
• Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning
• Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization
• A Data-Efficient Deep Learning Approach for Deployable Multimodal Social Robots
• Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars
• Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning
• ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay
• A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions
• Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation
• Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning
• Analysing Results from AI Benchmarks: Key Indicators and How to Obtain Them
• Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field
• Explanation-Aware Experience Replay in Rule-Dense Environments
• Exploration-Enhanced POLITEX
• Experience Replay with Likelihood-free Importance Weights
• A Human Mixed Strategy Approach to Deep Reinforcement Learning
• Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control
• Forward-Backward Reinforcement Learning
• Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning
• Applications of Deep Reinforcement Learning in Communications and Networking: A Survey
• Balancing a CartPole System with Reinforcement Learning -- A Tutorial
• Deep Reinforcement Learning and Transportation Research: A Comprehensive Review
• Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning
• Accelerating Reinforcement Learning through GPU Atari Emulation
• Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing
• AI-Based Autonomous Line Flow Control via Topology Adjustment for Maximizing Time-Series ATCs
• Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning
• Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment
• Experience Replay Using Transition Sequences
• CPU frequency scheduling of real-time applications on embedded devices with temporal encoding-based deep reinforcement learning
• Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
• Multi-agent Reinforcement Learning Accelerated MCMC on Multiscale Inversion Problem
• L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning
• Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis
• Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey
• Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challenges
• Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey
• Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
• Learning Heuristic Search via Imitation
• On Multi-Agent Learning in Team Sports Games
• Average AoI Minimization for Energy Harvesting Relay-aided Status Update Network Using Deep Reinforcement Learning
• CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning
• Counterfactual Data Augmentation using Locally Factored Dynamics
• Learning-to-Ask: Knowledge Acquisition via 20 Questions
• Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning
• Show Us the Way: Learning to Manage Dialog from Demonstrations
• Double Prioritized State Recycled Experience Replay
• Self-Imitation Learning via Generalized Lower Bound Q-learning
• Deep Reinforcement Learning With Macro-Actions
• Dynamic Experience Replay
• Learning to Multi-Task by Active Sampling
• Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in Sepsis Patients
• A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents
• Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning
• Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization
• Reinforcement Learning-based Switching Controller for a Milliscale Robot in a Constrained Environment
• A Deep Reinforcement Learning Approach for Global Routing
• A Dual-Hormone Closed-Loop Delivery System for Type 1 Diabetes Using Deep Reinforcement Learning
• Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL
• Automating Reinforcement Learning with Example-based Resets
• Configurable Agent With Reward As Input: A Play-Style Continuum Generation
• ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
• Proximal Policy Optimization with Adaptive Threshold for Symmetric Relative Density Ratio
• Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
• A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures
• Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments
• MOVI: A Model-Free Approach to Dynamic Fleet Management
• Assumed Density Filtering Q-learning
• Continuous-action Reinforcement Learning for Playing Racing Games: Comparing SPG to PPO
• Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing
• ARCADe: A Rapid Continual Anomaly Detector
• The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning
• Learning Symbolic Rules for Interpretable Deep Reinforcement Learning
• Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
• Direct and indirect reinforcement learning
• The PlayStation Reinforcement Learning Environment (PSXLE)
• Adapting Behaviour for Learning Progress
• Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme
• Learning to Control DC Motor for Micromobility in Real Time with Reinforcement Learning
• Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic
• Self-Imitation Advantage Learning
• Return-based Scaling: Yet Another Normalisation Trick for Deep RL
• Continuous Coordination As a Realistic Scenario for Lifelong Learning
• Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
• Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition
• Language Expansion In Text-Based Games
• DQN with model-based exploration: efficient learning on environments with sparse rewards
• Hierarchical Reinforcement Learning Method for Autonomous Vehicle Behavior Planning
• Online Distillation with Continual Learning for Cyclic Domain Shifts
• Learning Index Selection with Structured Action Spaces
• BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
• Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms
• Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning
• Reinforcement Learning with Non-Cumulative Objective
• The Effects of Memory Replay in Reinforcement Learning
• Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback
• Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning
• Learning Vision-based Reactive Policies for Obstacle Avoidance
• Sampled Policy Gradient for Learning to Play the Game Agar.io
• Auto-MAP: A DQN Framework for Exploring Distributed Execution Plans for DNN Workloads
• Counterfactual experience augmented off-policy reinforcement learning
• DiGrad: Multi-Task Reinforcement Learning with Shared Actions
• A hierarchical spatial-aware algorithm with efficient reinforcement learning for human-robot task planning and allocation in production
• Combinational Q-Learning for Dou Di Zhu
• Investigating Recurrence and Eligibility Traces in Deep Q-Networks
• Explainable AI: Deep Reinforcement Learning Agents for Residential Demand Side Cost Savings in Smart Grids
• Influence-Based Multi-Agent Exploration
• Automated Play-Testing Through RL Based Human-Like Play-Styles Generation
• Deep W-Networks: Solving Multi-Objective Optimisation Problems With Deep Reinforcement Learning
• Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search
• How Much Do Unstated Problem Constraints Limit Deep Robotic Reinforcement Learning?
• Challenges of Context and Time in Reinforcement Learning: Introducing Space Fortress as a Benchmark
• Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL
• A Visual Communication Map for Multi-Agent Deep Reinforcement Learning
• A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation
• Developing an OpenAI Gym-compatible framework and simulation environment for testing Deep Reinforcement Learning agents solving the Ambulance Location Problem
• Building Machines that Learn and Think for Themselves: Commentary on Lake et al., Behavioral and Brain Sciences, 2017
• FNAS: Uncertainty-Aware Fast Neural Architecture Search
• Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
• Offline Reinforcement Learning with Pseudometric Learning
• Deep Reinforcement Learning in Fluid Mechanics: a promising method for both Active Flow Control and Shape Optimization
• An Off-policy Policy Gradient Theorem Using Emphatic Weightings
• Data-driven battery operation for energy arbitrage using rainbow deep reinforcement learning
• Temporal Difference Learning with Neural Networks - Study of the Leakage Propagation Problem
• Off-Policy Risk-Sensitive Reinforcement Learning Based Constrained Robust Optimal Control
• Enhancing a Neurocognitive Shared Visuomotor Model for Object Identification, Localization, and Grasping With Learning From Auxiliary Tasks
• AMBER: Adaptive Multi-Batch Experience Replay for Continuous Action Control
• Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
• CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
• HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents
• Unsupervised Learning of KB Queries in Task-Oriented Dialogs
• Intrinsic Motivation Driven Intuitive Physics Learning using Deep Reinforcement Learning with Intrinsic Reward Normalization
• Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning
• Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions
• Importance Resampling for Off-policy Prediction
• Pedestrian Collision Avoidance for Autonomous Vehicles at Unsignalized Intersection Using Deep Q-Network
• V2I Connectivity-Based Dynamic Queue-Jump Lane for Emergency Vehicles: A Deep Reinforcement Learning Approach
• Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound
• Adaptive Height Optimisation for Cellular-Connected UAVs using Reinforcement Learning
• Q-DeckRec: A Fast Deck Recommendation System for Collectible Card Games
• Learning with Stochastic Guidance for Navigation
• Adaptive Ordered Information Extraction with Deep Reinforcement Learning
• Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space
• Economic Battery Storage Dispatch with Deep Reinforcement Learning from Rule-Based Demonstrations
• Modern Subsampling Methods for Large-Scale Least Squares Regression
• Safe Deep Q-Network for Autonomous Vehicles at Unsignalized Intersection
• Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
• REPAINT: Knowledge Transfer in Deep Reinforcement Learning
• Correcting Experience Replay for Multi-Agent Communication
• Model-Based Episodic Memory Induces Dynamic Hybrid Controls
• PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning
• Review, Analysis and Design of a Comprehensive Deep Reinforcement Learning Framework
• On Catastrophic Interference in Atari 2600 Games
• Stacked Auto Encoder Based Deep Reinforcement Learning for Online Resource Scheduling in Large-Scale MEC Networks
• Distributed Soft Actor-Critic with Multivariate Reward Representation and Knowledge Distillation
• Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi-Task Learning
• A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots
• Stochastic Reweighted Gradient Descent
• Tutorial and Survey on Probabilistic Graphical Model and Variational Inference in Deep Reinforcement Learning
• Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning
• Continuous Control for Searching and Planning with a Learned Model
• Policy Search by Target Distribution Learning for Continuous Control
• CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
• Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing
• Relationship Explainable Multi-objective Reinforcement Learning with Semantic Explainability Generation
• Relationship Explainable Multi-objective Optimization Via Vector Value Function Based Reinforcement Learning
• Program Synthesis Through Reinforcement Learning Guided Tree Search
• An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms
• Join Query Optimization with Deep Reinforcement Learning Algorithms
• CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++
• How Transferable are the Representations Learned by Deep Q Agents?
• Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning
• Competitive Experience Replay
• Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning
• A Dual Memory Structure for Efficient Use of Replay Memory in Deep Reinforcement Learning
• Meta-Learning with Hessian-Free Approach in Deep Neural Nets Training
• Goal-oriented Trajectories for Efficient Exploration
• Guided Exploration with Proximal Policy Optimization using a Single Demonstration
• Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
• Simulating multi-exit evacuation using deep reinforcement learning
• Deep Curiosity Loops in Social Environments
• Deep Reinforcement Learning Based Spectrum Allocation in Integrated Access and Backhaul Networks
• Towards Runtime Verification of Programmable Switches
• A Comparative Analysis of Deep Reinforcement Learning-enabled Freeway Decision-making for Automated Vehicles
• Biologically inspired architectures for sample-efficient deep reinforcement learning
• Sequential Search with Off-Policy Reinforcement Learning
• Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network Slicing
• Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors
• A Deep Learning Approach to Grasping the Invisible
• Compression and Localization in Reinforcement Learning for ATARI Games
• Non-decreasing Quantile Function Network with Efficient Exploration for Distributional Reinforcement Learning
• Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction
• Generating Socially Acceptable Perturbations for Efficient Evaluation of Autonomous Vehicles
• Amplifying the Imitation Effect for Reinforcement Learning of UCAV's Mission Execution
• Learning Diverse Policies with Soft Self-Generated Guidance
• Informative Path Planning for Mobile Sensing with Reinforcement Learning
• Fast Reinforcement Learning for Anti-jamming Communications
• Reinforcement Learning with Latent Flow
• Reinforcement Learning for Autonomous Defence in Software-Defined Networking
• Task2Morph: Differentiable Task-inspired Framework for Contact-Aware Robot Design
• Measuring Progress in Deep Reinforcement Learning Sample Efficiency
• Neural Fitted Q Iteration based Optimal Bidding Strategy in Real Time Reactive Power Market_1
• Questions to Guide the Future of Artificial Intelligence Research
• Learning active learning at the crossroads? evaluation and discussion
• Is Q-Learning Provably Efficient? An Extended Analysis
• Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
• Episodic Self-Imitation Learning with Hindsight
• Improvements on Hindsight Learning
• Improving the sample-efficiency of neural architecture search with reinforcement learning
• Convolutional Reservoir Computing for World Models
• Momentum-based Accelerated Q-learning
• Deictic Image Maps: An Abstraction For Learning Pose Invariant Manipulation Policies
• Which Channel to Ask My Question? Personalized Customer Service Request Stream Routing using Deep Reinforcement Learning
• Deep Reinforcement Learning for Playing 2.5D Fighting Games
• Reinforcement Learning with Convolutional Reservoir Computing
• Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings
• Individual specialization in multi-task environments with multiagent reinforcement learners
• Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline
• Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search
• On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning
• Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios
• Energy-Efficient Parking Analytics System using Deep Reinforcement Learning
• Discrete-to-Deep Supervised Policy Learning
• Interactive Machine Comprehension with Information Seeking Agents
• Prioritized Guidance for Efficient Multi-Agent Reinforcement Learning Exploration
• Reinforcement Learning and Video Games
• CoachNet: An Adversarial Sampling Approach for Reinforcement Learning
• Modelling resource allocation in uncertain system environment through deep reinforcement learning
• Reinforcement Learning Assisted Load Test Generation for E-Commerce Applications
• Accelerated Target Updates for Q-learning
• Efficient Automatic Meta Optimization Search for Few-Shot Learning
• Uniform Sampling over Episode Difficulty
• Deep reinforcement learning for RAN optimization and control
• Sentiment Analysis for Reinforcement Learning
• Decentralized Deep Reinforcement Learning for Network Level Traffic Signal Control
• Shared Learning : Enhancing Reinforcement in $Q$-Ensembles
• Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learning
• BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning
• Episodic Memory for Learning Subjective-Timescale Models
• Enhancing Reinforcement Learning Through Guided Search
• ACDER: Augmented Curiosity-Driven Experience Replay
• Deep Reinforcement Learning with Surrogate Agent-Environment Interface
• An adaptive synchronization approach for weights of deep reinforcement learning
• Continuous Deep Q-Learning with Simulator for Stabilization of Uncertain Discrete-Time Systems
• Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings
• Improving Intelligence of Evolutionary Algorithms Using Experience Share and Replay
• Generalization in Text-based Games via Hierarchical Reinforcement Learning
• Ranking Policy Gradient
• Reinforcement Learning Approach to Active Learning for Image Classification
• Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue
• An Asynchronous Updating Reinforcement Learning Framework for Task-oriented Dialog System
• Biological Blueprints for Next Generation AI Systems
• Unbiased Deep Reinforcement Learning: A General Training Framework for Existing and Future Algorithms
• Cross Modality 3D Navigation Using Reinforcement Learning and Neural Style Transfer
• Discrete linear-complexity reinforcement learning in continuous action spaces for Q-learning algorithms
• Lineage Evolution Reinforcement Learning
• Generative Exploration and Exploitation
• High Performance Across Two Atari Paddle Games Using the Same Perceptual Control Architecture Without Training
• Generative Adversarial Imagination for Sample Efficient Deep Reinforcement Learning