Addressing Function Approximation Error in Actor-Critic Methods

Abstract

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the critic. Our algorithm builds on Double Q-learning, by taking the minimum value between a pair of critics to limit overestimation. We draw the connection between target networks and overestimation bias, and suggest delaying policy updates to reduce per-update error and further improve performance. We evaluate our method on the suite of OpenAI gym tasks, outperforming the state of the art in every environment tested.

Accepted at ICML 2018

References in corpus (8)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Trust Region Policy Optimization
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning
• Data-efficient Deep Reinforcement Learning for Dexterous Manipulation
• Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening
• Smoothed Action Value Functions for Learning Gaussian Policies

Cited by in corpus (345)

• Soft Actor-Critic Algorithms and Applications
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
• Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
• Behavior Regularized Offline Reinforcement Learning
• MOPO: Model-based Offline Policy Optimization
• Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning
• Benchmarking Model-Based Reinforcement Learning
• Federated Reinforcement Learning: Techniques, Applications, and Open Challenges
• Soft Actor-Critic for Discrete Action Settings
• Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
• Recent advances in applying deep reinforcement learning for flow control: perspectives and future directions
• MOReL : Model-Based Offline Reinforcement Learning
• Transfer Learning in Deep Reinforcement Learning: A Survey
• Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review
• RLOC: Terrain-Aware Legged Locomotion using Reinforcement Learning and Optimal Control
• Prioritized Experience-based Reinforcement Learning with Human Guidance for Autonomous Driving
• 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
• An Optimistic Perspective on Offline Reinforcement Learning
• Deep Reinforcement Learning for Black-Box Testing of Android Apps
• CEM-RL: Combining evolutionary and gradient-based methods for policy search
• Quasi-hyperbolic momentum and Adam for deep learning
• AlgaeDICE: Policy Gradient from Arbitrary Experience
• Proximal Distilled Evolutionary Reinforcement Learning
• Deep Reinforcement Learning Approach for Trading Automation in The Stock Market
• Exploring Model-based Planning with Policy Networks
• A Functional Architecture for 6G Special Purpose Industrial IoT Networks
• Deep Reinforcement Learning for RIS-aided Multiuser Full-Duplex Secure Communications with Hardware Impairments
• 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
• t-Soft Update of Target Network for Deep Reinforcement Learning
• Towards Characterizing Divergence in Deep Q-Learning
• A Self-adaptive SAC-PID Control Approach based on Reinforcement Learning for Mobile Robots
• Unified Automatic Control of Vehicular Systems with Reinforcement Learning
• Real-time Cooperative Vehicle Coordination at Unsignalized Road Intersections
• An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics
• COMBO: Conservative Offline Model-Based Policy Optimization
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
• Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems
• rlpyt: A Research Code Base for Deep Reinforcement Learning in PyTorch
• Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?
• A reinforcement learning approach to rare trajectory sampling
• Softmax Deep Double Deterministic Policy Gradients
• Robust Reinforcement Learning on State Observations with Learned Optimal Adversary
• Multi-condition multi-objective optimization using deep reinforcement learning
• Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approach
• Off-Policy Multi-Agent Decomposed Policy Gradients
• Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning
• Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox
• CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning
• Exploration and Regularization of the Latent Action Space in Recommendation
• Model-Augmented Actor-Critic: Backpropagating through Paths
• Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past
• Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization
• Neural Ordinary Differential Equation Control of Dynamics on Graphs
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
• Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
• Inclined Quadrotor Landing using Deep Reinforcement Learning
• Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control
• TD-Regularized Actor-Critic Methods
• A Reinforcement Learning Approach for Transient Control of Liquid Rocket Engines
• Cooperative Behavior Planning for Automated Driving using Graph Neural Networks
• Robust Quadruped Jumping via Deep Reinforcement Learning
• BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
• CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
• Model-free Deep Reinforcement Learning for Urban Autonomous Driving
• Real-world validation of safe reinforcement learning, model predictive control and decision tree-based home energy management systems
• Randomized Ensembled Double Q-Learning: Learning Fast Without a Model
• Exploration of Artificial Intelligence-oriented Power System Dynamic Simulators
• Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning
• Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints
• TriFinger: An Open-Source Robot for Learning Dexterity
• Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs
• Learning Self-Imitating Diverse Policies
• Forward and inverse reinforcement learning sharing network weights and hyperparameters
• Deep Reinforcement Learning based Local Planner for UAV Obstacle Avoidance using Demonstration Data
• Probing the Theoretical and Computational Limits of Dissipative Design
• ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning
• How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?
• Learning to Assist Drone Landings
• REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning
• Automatic Intersection Management in Mixed Traffic Using Reinforcement Learning and Graph Neural Networks
• Optimistic Reinforcement Learning by Forward Kullback-Leibler Divergence Optimization
• Energy-Efficient Control Adaptation with Safety Guarantees for Learning-Enabled Cyber-Physical Systems
• Formulation and validation of a car-following model based on deep reinforcement learning
• Generalizable Episodic Memory for Deep Reinforcement Learning
• Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients
• Learning to Manipulate Deformable Objects without Demonstrations
• Deep reinforcement learning for smart calibration of radio telescopes
• Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
• Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
• Experience Replay with Likelihood-free Importance Weights
• Map-based Experience Replay: A Memory-Efficient Solution to Catastrophic Forgetting in Reinforcement Learning
• Regularization Matters in Policy Optimization
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
• AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
• Reinforcement Learning for Shared Autonomy Drone Landings
• Dynamics-aware Embeddings
• A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
• Offline RL Without Off-Policy Evaluation
• Learning Personalized Human-Aware Robot Navigation Using Virtual Reality Demonstrations from a User Study
• On the model-based stochastic value gradient for continuous reinforcement learning
• STAP: Sequencing Task-Agnostic Policies
• Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods
• Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
• Hierarchical Reinforcement Learning Framework for Stochastic Spaceflight Campaign Design
• Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments
• Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment
• Discretizing Continuous Action Space for On-Policy Optimization
• QoS-Aware Load Balancing in Wireless Networks using Clipped Double Q-Learning
• RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
• Multi-agent Reinforcement Learning Accelerated MCMC on Multiscale Inversion Problem
• Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling
• UniCon: Universal Neural Controller For Physics-based Character Motion
• D2RL: Deep Dense Architectures in Reinforcement Learning
• Observation Space Matters: Benchmark and Optimization Algorithm
• 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
• Reinforcement learning pulses for transmon qubit entangling gates
• Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation
• Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning
• Robust Reinforcement Learning via Adversarial training with Langevin Dynamics
• Counterfactual Data Augmentation using Locally Factored Dynamics
• Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations
• Self-Imitation Learning via Generalized Lower Bound Q-learning
• Network Slicing via Transfer Learning aided Distributed Deep Reinforcement Learning
• GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values
• Robust optimization for quantum reinforcement learning control using partial observations
• Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning
• Fairness-aware Competitive Bidding Influence Maximization in Social Networks
• Case Study: Verifying the Safety of an Autonomous Racing Car with a Neural Network Controller
• Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning
• Explainable Deep Reinforcement Learning for UAV Autonomous Navigation
• Robotic Surgery With Lean Reinforcement Learning
• End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear Model Predictive Control
• Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)
• ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learning
• Composing Task-Agnostic Policies with Deep Reinforcement Learning
• Multi-task Batch Reinforcement Learning with Metric Learning
• Model-Reference Reinforcement Learning Control of Autonomous Surface Vehicles with Uncertainties
• Batch-Constrained Reinforcement Learning for Dynamic Distribution Network Reconfiguration
• C-Learning: Learning to Achieve Goals via Recursive Classification
• Optimizing Mixed Autonomy Traffic Flow With Decentralized Autonomous Vehicles and Multi-Agent RL
• Maximum Mutation Reinforcement Learning for Scalable Control
• Why People Skip Music? On Predicting Music Skips using Deep Reinforcement Learning
• ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning
• Optimal mesh generation for a non-iterative grid-converged solution of flow through a blade passage using deep reinforcement learning
• Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
• ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning
• An Enhanced Graph Representation for Machine Learning Based Automatic Intersection Management
• A reinforcement learning path planning approach for range-only underwater target localization with autonomous vehicles
• Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning
• Computational Performance of Deep Reinforcement Learning to find Nash Equilibria
• Adaptive Online Planning for Continual Lifelong Learning
• Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
• Integration of Reinforcement Learning Based Behavior Planning With Sampling Based Motion Planning for Automated Driving
• Distributed Voltage Regulation of Active Distribution System Based on Enhanced Multi-agent Deep Reinforcement Learning
• The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning
• Sim2Real for Peg-Hole Insertion with Eye-in-Hand Camera
• Measuring Visual Generalization in Continuous Control from Pixels
• Deep Reinforcement Learning for Autonomous Ground Vehicle Exploration Without A-Priori Maps
• How to Make Deep RL Work in Practice
• Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning
• Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
• A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
• Deep Residual Reinforcement Learning
• How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning
• SOAC: The Soft Option Actor-Critic Architecture
• Policy-Aware Model Learning for Policy Gradient Methods
• Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling
• EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
• Dynamic Control of a Fiber Manufacturing Process using Deep Reinforcement Learning
• RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion
• Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents
• Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion
• Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies
• A Maximum Mutual Information Framework for Multi-Agent Reinforcement Learning
• Instabilities of Offline RL with Pre-Trained Neural Representation
• Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling
• Inter-Cell Network Slicing With Transfer Learning Empowered Multi-Agent Deep Reinforcement Learning
• A Transferability Metric Using Scene Similarity and Local Map Observation for DRL Navigation
• Reinforcement Learning vs. Gradient-Based Optimisation for Robust Energy Landscape Control of Spin-1/2 Quantum Networks
• Average-Reward Off-Policy Policy Evaluation with Function Approximation
• Maximum Reward Formulation In Reinforcement Learning
• Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners
• Regularizing Trajectory Optimization with Denoising Autoencoders
• Model Imitation for Model-Based Reinforcement Learning
• GRAC: Self-Guided and Self-Regularized Actor-Critic
• Generalized Off-Policy Actor-Critic
• Learning Agile Locomotion via Adversarial Training
• A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms
• Feature-Based Interpretable Reinforcement Learning based on State-Transition Models
• Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning
• Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation
• Zeroth-order Deterministic Policy Gradient
• Learning to Engage with Interactive Systems: A Field Study on Deep Reinforcement Learning in a Public Museum
• Generating Automatic Curricula via Self-Supervised Active Domain Randomization
• Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
• Non-local Policy Optimization via Diversity-regularized Collaborative Exploration
• Interactive Visualization for Debugging RL
• FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism
• A Max-Min Entropy Framework for Reinforcement Learning
• Offline Reinforcement Learning with Pseudometric Learning
• Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
• Breaking the Deadly Triad with a Target Network
• Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty
• Teach Biped Robots to Walk via Gait Principles and Reinforcement Learning with Adversarial Critics
• Steady State Analysis of Episodic Reinforcement Learning
• Efficient Reservoir Management through Deep Reinforcement Learning
• A Learning Framework for High Precision Industrial Assembly
• Learning Guidance Rewards with Trajectory-space Smoothing
• Coordination in Adversarial Sequential Team Games via Multi-Agent Deep Reinforcement Learning
• Solving Challenging Dexterous Manipulation Tasks With Trajectory Optimisation and Reinforcement Learning
• Caching Transient Content for IoT Sensing: Multi-Agent Soft Actor-Critic
• Neural Style Transfer with Twin-Delayed DDPG for Shared Control of Robotic Manipulators
• Variance-Reduced Off-Policy Memory-Efficient Policy Search
• HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents
• P3O: Policy-on Policy-off Policy Optimization
• Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation
• Regularized Behavior Value Estimation
• Risk-Aware Continuous Control with Neural Contextual Bandits
• Deep Reinforcement Learning for Process Synthesis
• Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
• Band-limited Soft Actor Critic Model
• Off-Policy Adversarial Inverse Reinforcement Learning
• A User's Guide to Calibrating Robotics Simulators
• Estimating Q(s,s') with Deep Deterministic Dynamics Gradients
• Sample-Efficient Automated Deep Reinforcement Learning
• Reward Tweaking: Maximizing the Total Reward While Planning for Short Horizons
• Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning
• Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning
• DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning
• Behavior-Guided Actor-Critic: Improving Exploration via Learning Policy Behavior Representation for Deep Reinforcement Learning
• Distributed Soft Actor-Critic with Multivariate Reward Representation and Knowledge Distillation
• Inter-Level Cooperation in Hierarchical Reinforcement Learning
• Recruitment-imitation Mechanism for Evolutionary Reinforcement Learning
• Learning Representations in Reinforcement Learning:An Information Bottleneck Approach
• Towards Automatic Actor-Critic Solutions to Continuous Control
• Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
• Approximate Model-Based Shielding for Safe Reinforcement Learning
• Proximal Policy Gradient: PPO with Policy Gradient
• Reinforcement Learning with Random Delays
• Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
• BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
• Learning Retrospective Knowledge with Reverse Reinforcement Learning
• Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System
• Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy
• Safe Exploration by Solving Early Terminated MDP
• Competitiveness of MAP-Elites against Proximal Policy Optimization on locomotion tasks in deterministic simulations
• Bi-level Actor-Critic for Multi-agent Coordination
• A Deep Reinforcement Learning Architecture for Multi-stage Optimal Control
• Discriminator Soft Actor Critic without Extrinsic Rewards
• Dual policy as self-model for planning
• Energy-based Surprise Minimization for Multi-Agent Value Factorization
• Zeroth-Order Supervised Policy Improvement
• Learning Diverse Policies with Soft Self-Generated Guidance
• Market-making with reinforcement-learning (SAC)
• Controlling earthquake-like instabilities using artificial intelligence
• Optimistic Distributionally Robust Policy Optimization
• Merging Deterministic Policy Gradient Estimations with Varied Bias-Variance Tradeoff for Effective Deep Reinforcement Learning
• Novel Policy Seeking with Constrained Optimization
• Uniform Priors for Data-Efficient Transfer
• Deep Learned Path Planning via Randomized Reward-Linked-Goals and Potential Space Applications
• OPAC: Opportunistic Actor-Critic
• An Intelligent Energy Management Framework for Hybrid-Electric Propulsion Systems Using Deep Reinforcement Learning
• PAC-Bayesian Soft Actor-Critic Learning
• Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning
• Hindsight Foresight Relabeling for Meta-Reinforcement Learning
• Logistic Q-Learning
• Reinforcement Learning for Vision-based Object Manipulation with Non-parametric Policy and Action Primitives
• Deep Reinforcement Learning with Linear Quadratic Regulator Regions
• Tuning Synaptic Connections instead of Weights by Genetic Algorithm in Spiking Policy Network
• Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control
• Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison
• On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction
• AMaze: An intuitive benchmark generator for fast prototyping of generalizable agents
• Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks
• Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
• Worrisome Properties of Neural Network Controllers and Their Symbolic Representations
• Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization
• Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
• Value-Based Reinforcement Learning for Continuous Control Robotic Manipulation in Multi-Task Sparse Reward Settings
• Dream and Search to Control: Latent Space Planning for Continuous Control
• ADER:Adapting between Exploration and Robustness for Actor-Critic Methods
• A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets
• Not Only Domain Randomization: Universal Policy with Embedding System Identification
• Learning Off-Policy with Online Planning
• APPLR: Adaptive Planner Parameter Learning from Reinforcement
• C-Learning: Horizon-Aware Cumulative Accessibility Estimation
• A survey of benchmarking frameworks for reinforcement learning
• Measuring Progress in Deep Reinforcement Learning Sample Efficiency
• PFPN: Continuous Control of Physically Simulated Characters using Particle Filtering Policy Network
• Advanced Policies: A First-Principles Path from Policy Gradient to Q-Learning
• Regularly Updated Deterministic Policy Gradient Algorithm
• MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning
• Reinforcement learning with world model
• Lyapunov-Based Reinforcement Learning for Decentralized Multi-Agent Control
• Which Channel to Ask My Question? Personalized Customer Service Request Stream Routing using Deep Reinforcement Learning
• Discrete Action On-Policy Learning with Action-Value Critic
• Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning
• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction
• Model-Augmented Q-learning
• Continuous Multi-objective Zero-touch Network Slicing via Twin Delayed DDPG and OpenAI Gym
• Policy Gradient RL Algorithms as Directed Acyclic Graphs
• Suspension Regulation of Medium-low-speed Maglev Trains via Deep Reinforcement Learning
• Biased Estimates of Advantages over Path Ensembles
• Weighted Entropy Modification for Soft Actor-Critic
• Locality-Sensitive Experience Replay for Online Recommendation
• Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies
• Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation
• A Model-free Deep Reinforcement Learning Approach To Maneuver A Quadrotor Despite Single Rotor Failure
• Efficient Reinforcement Learning Development with RLzoo
• Planning with Exploration: Addressing Dynamics Bottleneck in Model-based Reinforcement Learning
• Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents
• Optimal Control-Based Baseline for Guided Exploration in Policy Gradient Methods
• Large Batch Experience Replay
• Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations
• Adaptation of Quadruped Robot Locomotion with Meta-Learning
• Cross Learning in Deep Q-Networks
• FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control
• Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
• Techniques Toward Optimizing Viewability in RTB Ad Campaigns Using Reinforcement Learning
• Playing optical tweezers with deep reinforcement learning: in virtual, physical and augmented environments
• Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics
• False Correlation Reduction for Offline Reinforcement Learning
• Functional Regularization for Reinforcement Learning via Learned Fourier Features
• Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning
• Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model
• Reconciling Spatial and Temporal Abstractions for Goal Representation
• Mechatronic Design of a Dribbling System for RoboCup Small Size Robot
• Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans
• Reinforcement Learning with Goal-Distance Gradient
• From proprioception to long-horizon planning in novel environments: A hierarchical RL model
• Model Embedding Model-Based Reinforcement Learning
• Evolutionary Stochastic Policy Distillation
• Evolution of Q Values for Deep Q Learning in Stable Baselines
• Efficient Hyperparameter Optimization for Physics-based Character Animation
• Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning
• Maximum Entropy Reinforcement Learning with Mixture Policies
• A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning