{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/ddpg","slug":"ddpg","name":"DDPG","full_name":"Deep Deterministic Policy Gradient","full_name_withheld":false,"description_markdown":"**DDPG**, or **Deep Deterministic Policy Gradient**, is an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. It combines the actor-critic approach with insights from [DQNs](https://paperswithcode.com/method/dqn): in particular, the insights that 1) the network is trained off-policy with samples from a replay buffer to minimize correlations between samples, and 2) the network is trained with a target Q network to give consistent targets during temporal difference backups. DDPG makes use of the same ideas along with [batch normalization](https://paperswithcode.com/method/batch-normalization).","description_state":"present","introduced_year":null,"introduced_by":{"title":"Continuous control with deep reinforcement learning","paper":"/paper/continuous-control-with-deep-reinforcement","first_author":"Timothy P. Lillicrap","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/continuous-control-with-deep-reinforcement"},"source":{"url":"https://arxiv.org/abs/1509.02971v6","title":"Continuous control with deep reinforcement learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Policy Gradient Methods","url":"/methods/category/policy-gradient-methods","pwc_aliases":[]}],"n_papers_tagged":218,"archive_num_papers":218,"papers_newest_first":[{"paper":null,"slug":"multi-objective-reinforcement-learning-for-6","title":"Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management","date":"2025-06-25","arxiv_id":"2506.20853","n_code_links":0,"syntology":null},{"paper":null,"slug":"reliable-critics-monotonic-improvement-and","title":"Reliable Critics: Monotonic Improvement and Convergence Guarantees for Reinforcement Learning","date":"2025-06-08","arxiv_id":"2506.07134","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-deep-reinforcement-learning-method","title":"A Novel Deep Reinforcement Learning Method for Computation Offloading in Multi-User Mobile Edge Computing with Decentralization","date":"2025-06-03","arxiv_id":"2506.02458","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-explorer-a-plug-in-reinforcement-learning","title":"LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models","date":"2025-05-21","arxiv_id":"2505.15293","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-based-4","title":"Deep reinforcement learning-based longitudinal control strategy for automated vehicles at signalised intersections","date":"2025-05-13","arxiv_id":"2505.08896","n_code_links":0,"syntology":null},{"paper":null,"slug":"moderate-actor-critic-methods-controlling","title":"Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss","date":"2025-04-14","arxiv_id":"2504.09929","n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-joint-security-and-delay","title":"Intelligent Joint Security and Delay Determinacy Performance Guarantee Strategy in RIS-Assisted IIoT Communication Systems","date":"2025-03-11","arxiv_id":"2503.08086","n_code_links":0,"syntology":null},{"paper":"/paper/evorl-a-gpu-accelerated-framework-for","slug":"evorl-a-gpu-accelerated-framework-for","title":"EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning","date":"2025-01-25","arxiv_id":"2501.15129","n_code_links":2,"syntology":null},{"paper":null,"slug":"federated-deep-reinforcement-learning-for-1","title":"Federated Deep Reinforcement Learning for Energy Efficient Multi-Functional RIS-Assisted Low-Earth Orbit Networks","date":"2025-01-19","arxiv_id":"2501.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"autoloop-fast-visual-slam-fine-tuning-through","title":"AutoLoop: Fast Visual SLAM Fine-tuning through Agentic Curriculum Learning","date":"2025-01-15","arxiv_id":"2501.09160","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-portfolio-optimization-via-augmented","title":"Dynamic Portfolio Optimization via Augmented DDPG with Quantum Price Levels-Based Trading Strategy","date":"2025-01-15","arxiv_id":"2501.08528","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-advantage-based-optimization-method-for","title":"An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space","date":"2024-12-17","arxiv_id":"2412.12605","n_code_links":0,"syntology":null},{"paper":null,"slug":"broad-critic-deep-actor-reinforcement","title":"Broad Critic Deep Actor Reinforcement Learning for Continuous Control","date":"2024-11-24","arxiv_id":"2411.15806","n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-efficient-action-manipulation-attack","title":"Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning","date":"2024-11-20","arxiv_id":"2411.13116","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantum-policy-gradient-in-reproducing-kernel","title":"Quantum Policy Gradient in Reproducing Kernel Hilbert Space","date":"2024-11-11","arxiv_id":"2411.06650","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-suboptimality-of-deterministic","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","date":"2024-10-15","arxiv_id":"2410.11833","n_code_links":0,"syntology":null},{"paper":null,"slug":"etgl-ddpg-a-deep-deterministic-policy","title":"ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control","date":"2024-10-07","arxiv_id":"2410.05225","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-deep-reinforcement-learning-for-volt","title":"Robust Deep Reinforcement Learning for Volt-VAR Optimization in Active Distribution System under Uncertainty","date":"2024-09-27","arxiv_id":"2409.18937","n_code_links":0,"syntology":null},{"paper":null,"slug":"shangus-deep-reinforcement-learning-meets","title":"FH-DRL: Exponential-Hyperbolic Frontier Heuristics with DRL for accelerated Exploration in Unknown Environments","date":"2024-07-26","arxiv_id":"2407.18892","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-cross-environment-hyperparameter-setting","title":"The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning","date":"2024-07-26","arxiv_id":"2407.18840","n_code_links":0,"syntology":null},{"paper":"/paper/reconfigurable-intelligent-surface-aided-21","slug":"reconfigurable-intelligent-surface-aided-21","title":"Reconfigurable Intelligent Surface Aided Vehicular Edge Computing: Joint Phase-shift Optimization and Multi-User Power Allocation","date":"2024-07-18","arxiv_id":"2407.13123","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-with-symmetric-1","title":"Deep reinforcement learning with symmetric data augmentation applied for aircraft lateral attitude tracking control","date":"2024-07-13","arxiv_id":"2407.11077","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-strategies-in","title":"Deep Reinforcement Learning Strategies in Finance: Insights into Asset Holding, Trading Behavior, and Purchase Diversity","date":"2024-06-29","arxiv_id":"2407.09557","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-comparison-of-deep-rl-algorithms-1","title":"Performance Comparison of Deep RL Algorithms for Mixed Traffic Cooperative Lane-Changing","date":"2024-06-25","arxiv_id":"2407.02521","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-dynamic-resource-allocation-and","title":"Towards Dynamic Resource Allocation and Client Scheduling in Hierarchical Federated Learning: A Two-Phase Deep Reinforcement Learning Approach","date":"2024-06-21","arxiv_id":"2406.14910","n_code_links":0,"syntology":null},{"paper":null,"slug":"value-improved-actor-critic-algorithms","title":"Value Improved Actor Critic Algorithms","date":"2024-06-03","arxiv_id":"2406.01423","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-reinforcement-learning-for-resource-1","title":"Meta Reinforcement Learning for Resource Allocation in Multi-Antenna UAV Network with Rate Splitting Multiple Access","date":"2024-05-18","arxiv_id":"2405.11306","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-control-reinforcement-learning","title":"Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms","date":"2024-04-16","arxiv_id":"2404.10645","n_code_links":0,"syntology":null},{"paper":null,"slug":"conservative-ddpg-pessimistic-rl-without","title":"Conservative DDPG -- Pessimistic RL without Ensemble","date":"2024-03-08","arxiv_id":"2403.05732","n_code_links":0,"syntology":null},{"paper":null,"slug":"fill-and-spill-deep-reinforcement-learning","title":"Fill-and-Spill: Deep Reinforcement Learning Policy Gradient Methods for Reservoir Operation Decision and Control","date":"2024-03-07","arxiv_id":"2403.04195","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-free-deep-deterministic-policy-gradient","title":"Model Free Deep Deterministic Policy Gradient Controller for Setpoint Tracking of Non-minimum Phase Systems","date":"2024-02-27","arxiv_id":"2402.17703","n_code_links":0,"syntology":null},{"paper":"/paper/flowpg-action-constrained-policy-gradient-1","slug":"flowpg-action-constrained-policy-gradient-1","title":"FlowPG: Action-constrained Policy Gradient with Normalizing Flows","date":"2024-02-07","arxiv_id":"2402.05149","n_code_links":1,"syntology":null},{"paper":null,"slug":"textit-minmaxmin-q-learning","title":"MinMaxMin $Q$-learning","date":"2024-02-03","arxiv_id":"2402.05951","n_code_links":0,"syntology":null},{"paper":null,"slug":"textit-sqt-textit-std-q-target","title":"SQT -- std $Q$-target","date":"2024-02-03","arxiv_id":"2402.05950","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-for-voltage","title":"Deep Reinforcement Learning for Voltage Control and Renewable Accommodation Using Spatial-Temporal Graph Information","date":"2024-01-29","arxiv_id":"2401.15848","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-enabled-priority-and-auction-based","title":"AI-enabled Priority and Auction-Based Spectrum Management for 6G","date":"2024-01-12","arxiv_id":"2401.06484","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-discounting-of-training-time-attacks","title":"Adaptive Discounting of Training Time Attacks","date":"2024-01-05","arxiv_id":"2401.02652","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiagent-copilot-approach-for-shared","title":"Multiagent Copilot Approach for Shared Autonomy between Human EEG and TD3 Deep Reinforcement Learning","date":"2023-12-22","arxiv_id":"2312.14458","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-fairness-aware-spectrum-auction-for","title":"Dynamic Fairness-Aware Spectrum Auction for Enhanced Licensed Shared Access in 6G Networks","date":"2023-12-20","arxiv_id":"2312.12867","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-reinforcement-learning-for","title":"Contextual Reinforcement Learning for Offshore Wind Farm Bidding","date":"2023-12-18","arxiv_id":"2312.10884","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-robotic-navigation-an-evaluation-of","title":"Enhancing Robotic Navigation: An Evaluation of Single and Multi-Objective Reinforcement Learning Strategies","date":"2023-12-13","arxiv_id":"2312.07953","n_code_links":0,"syntology":null},{"paper":null,"slug":"finite-horizon-reinforcement-learning-in","title":"Finite Horizon Multi-Agent Reinforcement Learning in Solving Optimal Control of State-Dependent Switched Systems","date":"2023-12-08","arxiv_id":"2312.04767","n_code_links":0,"syntology":null},{"paper":null,"slug":"epidemic-decision-making-system-based","title":"Epidemic Decision-making System Based Federated Reinforcement Learning","date":"2023-11-03","arxiv_id":"2311.01749","n_code_links":0,"syntology":null},{"paper":"/paper/dsac-t-distributional-soft-actor-critic-with","slug":"dsac-t-distributional-soft-actor-critic-with","title":"Distributional Soft Actor-Critic with Three Refinements","date":"2023-10-09","arxiv_id":"2310.05858","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jingliang-duan/dsac-t","jingliang-duan/dsac-v2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"energy-management-in-a-cooperative-energy","title":"Energy Management in a Cooperative Energy Harvesting Wireless Sensor Network","date":"2023-10-09","arxiv_id":"2310.05911","n_code_links":0,"syntology":null},{"paper":null,"slug":"cad-clustering-and-deep-reinforcement","title":"CAD: Clustering And Deep Reinforcement Learning Based Multi-Period Portfolio Management Strategy","date":"2023-10-02","arxiv_id":"2310.01319","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-data-efficiency-in-reinforcement","slug":"enhancing-data-efficiency-in-reinforcement","title":"Enhancing data efficiency in reinforcement learning: a novel imagination mechanism based on mesh information propagation","date":"2023-09-25","arxiv_id":"2309.14243","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-long-n-step-surrogate-stage-reward-for-deep","title":"A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/double-gumbel-q-learning","slug":"double-gumbel-q-learning","title":"Double Gumbel Q-Learning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-driven-patient-monitoring-with-multi-agent","title":"Adaptive Multi-Agent Deep Reinforcement Learning for Timely Healthcare Interventions","date":"2023-09-20","arxiv_id":"2309.10980","n_code_links":0,"syntology":null},{"paper":null,"slug":"vehicles-control-collision-avoidance-using","title":"Vehicles Control: Collision Avoidance using Federated Deep Reinforcement Learning","date":"2023-08-04","arxiv_id":"2308.02614","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-reinforcement-learning-techniques","slug":"exploring-reinforcement-learning-techniques","title":"Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment","date":"2023-07-20","arxiv_id":"2307.11166","n_code_links":1,"syntology":null},{"paper":null,"slug":"safe-reinforcement-learning-for-strategic","title":"Safe Reinforcement Learning for Strategic Bidding of Virtual Power Plants in Day-Ahead Markets","date":"2023-07-11","arxiv_id":"2307.05812","n_code_links":0,"syntology":null},{"paper":null,"slug":"safety-aware-task-composition-for-discrete","title":"Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning","date":"2023-06-29","arxiv_id":"2306.17033","n_code_links":0,"syntology":null},{"paper":null,"slug":"action-and-trajectory-planning-for-urban","title":"Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning","date":"2023-06-28","arxiv_id":"2306.15968","n_code_links":0,"syntology":null},{"paper":null,"slug":"safe-efficient-comfort-and-energy-saving","title":"Safe, Efficient, Comfort, and Energy-saving Automated Driving through Roundabout Based on Deep Reinforcement Learning","date":"2023-06-20","arxiv_id":"2306.11465","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-practical-robust-reinforcement-learning","title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm","date":"2023-05-11","arxiv_id":"2305.06657","n_code_links":0,"syntology":null},{"paper":"/paper/simple-noisy-environment-augmentation-for","slug":"simple-noisy-environment-augmentation-for","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","date":"2023-05-04","arxiv_id":"2305.02882","n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-deep-reinforcement-learning-for-thz","title":"Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSI","date":"2023-04-25","arxiv_id":"2304.13109","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-ris-aided-eh-noma-networks-a-deep","title":"Active RIS-aided EH-NOMA Networks: A Deep Reinforcement Learning Approach","date":"2023-04-11","arxiv_id":"2304.12184","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-management-of-multi-mode-plug-in","title":"Energy Management of Multi-mode Plug-in Hybrid Electric Vehicle using Multi-agent Deep Reinforcement Learning","date":"2023-03-16","arxiv_id":"2303.09658","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-strategy-oriented-bayesian-soft-actor","title":"A Strategy-Oriented Bayesian Soft Actor-Critic Model","date":"2023-03-07","arxiv_id":"2303.04193","n_code_links":0,"syntology":null},{"paper":null,"slug":"combating-uncertainties-in-wind-and","title":"Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting","date":"2023-02-27","arxiv_id":"2302.14094","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-the-gumbel-softmax-in-maddpg","slug":"revisiting-the-gumbel-softmax-in-maddpg","title":"Revisiting the Gumbel-Softmax in MADDPG","date":"2023-02-23","arxiv_id":"2302.11793","n_code_links":1,"syntology":null},{"paper":null,"slug":"uav-path-planning-employing-mpc-reinforcement","title":"UAV Path Planning Employing MPC- Reinforcement Learning Method Considering Collision Avoidance","date":"2023-02-21","arxiv_id":"2302.10669","n_code_links":0,"syntology":null},{"paper":"/paper/smart-6g-sky-for-green-mobile-iot-networks","slug":"smart-6g-sky-for-green-mobile-iot-networks","title":"Smart 6G Sky for Green Mobile IOT Networks","date":"2023-02-15","arxiv_id":"2302.09022","n_code_links":1,"syntology":null},{"paper":null,"slug":"ris-assisted-jamming-rejection-and-path","title":"RIS-Assisted Jamming Rejection and Path Planning for UAV-Borne IoT Platform: A New Deep Reinforcement Learning Framework","date":"2023-02-10","arxiv_id":"2302.04994","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-for-traffic-light-1","title":"Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systems","date":"2023-02-04","arxiv_id":"2302.03669","n_code_links":0,"syntology":null},{"paper":null,"slug":"v2n-service-scaling-with-deep-reinforcement","title":"V2N Service Scaling with Deep Reinforcement Learning","date":"2023-01-30","arxiv_id":"2301.13324","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-deep-reinforcement-learning-based-2","title":"A Novel Deep Reinforcement Learning-based Approach for Enhancing Spectral Efficiency of IRS-assisted Wireless Systems","date":"2023-01-24","arxiv_id":"2302.14706","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-geometry-of-reinforcement-learning-in","title":"On the Geometry of Reinforcement Learning in Continuous State and Action Spaces","date":"2022-12-29","arxiv_id":"2301.00009","n_code_links":0,"syntology":null},{"paper":null,"slug":"off-policy-deep-reinforcement-learning-1","title":"Off-Policy Deep Reinforcement Learning Algorithms for Handling Various Robotic Manipulator Tasks","date":"2022-12-11","arxiv_id":"2212.05572","n_code_links":0,"syntology":null},{"paper":null,"slug":"cacto-continuous-actor-critic-with-trajectory","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","date":"2022-11-12","arxiv_id":"2211.06625","n_code_links":0,"syntology":null},{"paper":null,"slug":"wind-power-forecasting-considering-data","title":"Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach","date":"2022-11-02","arxiv_id":"2211.02674","n_code_links":0,"syntology":null},{"paper":"/paper/aacher-assorted-actor-critic-deep","slug":"aacher-assorted-actor-critic-deep","title":"AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay","date":"2022-10-24","arxiv_id":"2210.12892","n_code_links":1,"syntology":null},{"paper":"/paper/multiagent-reinforcement-learning-based-on","slug":"multiagent-reinforcement-learning-based-on","title":"Multiagent Reinforcement Learning Based on Fusion-Multiactor-Attention-Critic for Multiple-Unmanned-Aerial-Vehicle Navigation Control","date":"2022-10-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"algorithmic-trading-using-continuous-action","title":"Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning","date":"2022-10-07","arxiv_id":"2210.03469","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimizing-human-assistance-augmenting-a","title":"Minimizing Human Assistance: Augmenting a Single Demonstration for Deep Reinforcement Learning","date":"2022-09-22","arxiv_id":"2209.11275","n_code_links":0,"syntology":null},{"paper":"/paper/goal-conditioned-q-learning-as-knowledge","slug":"goal-conditioned-q-learning-as-knowledge","title":"Goal-Conditioned Q-Learning as Knowledge Distillation","date":"2022-08-28","arxiv_id":"2208.13298","n_code_links":1,"syntology":null},{"paper":"/paper/bsac-bayesian-strategy-network-based-soft","slug":"bsac-bayesian-strategy-network-based-soft","title":"Bayesian Soft Actor-Critic: A Directed Acyclic Strategy Graph Based Deep Reinforcement Learning","date":"2022-08-11","arxiv_id":"2208.06033","n_code_links":2,"syntology":null},{"paper":null,"slug":"deep-reinforcement-learning-for-dynamic-4","title":"Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning based Recommendation","date":"2022-08-10","arxiv_id":"2208.05142","n_code_links":0,"syntology":null},{"paper":"/paper/performance-comparison-of-deep-rl-algorithms","slug":"performance-comparison-of-deep-rl-algorithms","title":"Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling","date":"2022-08-01","arxiv_id":"2208.00728","n_code_links":1,"syntology":null},{"paper":null,"slug":"distributional-actor-critic-ensemble-for","title":"Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control","date":"2022-07-27","arxiv_id":"2207.13730","n_code_links":0,"syntology":null},{"paper":"/paper/abstract-demonstrations-and-adaptive","slug":"abstract-demonstrations-and-adaptive","title":"Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning","date":"2022-07-19","arxiv_id":"2207.09243","n_code_links":1,"syntology":null},{"paper":null,"slug":"autonomous-platoon-control-with-integrated","title":"Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming","date":"2022-06-15","arxiv_id":"2206.07536","n_code_links":0,"syntology":null},{"paper":null,"slug":"computation-offloading-and-resource-1","title":"Computation Offloading and Resource Allocation in F-RANs: A Federated Deep Reinforcement Learning Approach","date":"2022-06-13","arxiv_id":"2206.05881","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-energy-dispatch-and-unit-commitment-in","title":"Joint Energy Dispatch and Unit Commitment in Microgrids Based on Deep Reinforcement Learning","date":"2022-06-03","arxiv_id":"2206.01663","n_code_links":0,"syntology":null},{"paper":"/paper/truly-deterministic-policy-optimization-1","slug":"truly-deterministic-policy-optimization-1","title":"Truly Deterministic Policy Optimization","date":"2022-05-30","arxiv_id":"2205.15379","n_code_links":1,"syntology":null},{"paper":null,"slug":"multiple-domain-cyberspace-attack-and-defense","title":"Multiple Domain Cyberspace Attack and Defense Game Based on Reward Randomization Reinforcement Learning","date":"2022-05-23","arxiv_id":"2205.10990","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-reinforcement-learning-for-star-riss-a","title":"Hybrid Reinforcement Learning for STAR-RISs: A Coupled Phase-Shift Model Based Beamformer","date":"2022-05-10","arxiv_id":"2205.05029","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-gaussian-mixture-critic-in-off","slug":"revisiting-gaussian-mixture-critic-in-off","title":"Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach","date":"2022-04-21","arxiv_id":"2204.10256","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-transformer-for-long","slug":"confidence-estimation-transformer-for-long","title":"Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching","date":"2022-04-10","arxiv_id":"2204.04612","n_code_links":1,"syntology":null},{"paper":null,"slug":"collaborative-intelligent-reflecting-surface","title":"Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning","date":"2022-03-26","arxiv_id":"2203.14152","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-parametric-stochastic-policy-gradient","title":"Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment","date":"2022-03-24","arxiv_id":"2203.14905","n_code_links":0,"syntology":null},{"paper":"/paper/microracer-a-didactic-environment-for-deep","slug":"microracer-a-didactic-environment-for-deep","title":"MicroRacer: a didactic environment for Deep Reinforcement Learning","date":"2022-03-20","arxiv_id":"2203.10494","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-reinforcement-learning-for-predictive","title":"Designing Heterogeneous GNNs with Desired Permutation Properties for Wireless Resource Allocation","date":"2022-03-08","arxiv_id":"2203.03906","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-based-robust-resource-allocation-in-end-to","title":"AI-based Robust Resource Allocation in End-to-End Network Slicing under Demand and CSI Uncertainties","date":"2022-02-10","arxiv_id":"2202.05131","n_code_links":0,"syntology":null},{"paper":"/paper/skrl-modular-and-flexible-library-for","slug":"skrl-modular-and-flexible-library-for","title":"skrl: Modular and Flexible Library for Reinforcement Learning","date":"2022-02-08","arxiv_id":"2202.03825","n_code_links":1,"syntology":null},{"paper":null,"slug":"ddpg-driven-deep-unfolding-with-adaptive","title":"DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning","date":"2022-01-20","arxiv_id":"2201.08477","n_code_links":0,"syntology":null},{"paper":null,"slug":"critic-algorithms-using-cooperative-networks","title":"Critic Algorithms using Cooperative Networks","date":"2022-01-19","arxiv_id":"2201.07839","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":218,"with_a_code_link":71,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":218,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":14,"papers_where_code_ran_first_page":"/method/ddpg/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":3,"url":"/method/ddpg/papers/2","json":"/method/ddpg/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/method/ddpg/papers/3","json":"/method/ddpg/papers/3.json","rows":18},{"order":"ran","page":1,"of":1,"url":"/method/ddpg/papers/ran/1","json":"/method/ddpg/papers/ran/1.json","rows":14}],"tasks":[{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":131},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":114},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":105},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":102},{"task":"/task/continuous-control","name":"Continuous Control","papers":36},{"task":"/task/continuous-control","name":"continuous-control","papers":34},{"task":"/task/q-learning","name":"Q-Learning","papers":17},{"task":"/task/mujoco","name":"MuJoCo","papers":16},{"task":"/task/openai-gym","name":"OpenAI Gym","papers":15},{"task":"/task/decision-making","name":"Decision Making","papers":14},{"task":"/task/management","name":"Management","papers":13},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":8},{"task":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","papers":6},{"task":"/task/scheduling","name":"Scheduling","papers":6},{"task":"/task/energy-management","name":"energy management","papers":6},{"task":"/task/diversity","name":"Diversity","papers":5},{"task":"/task/federated-learning","name":"Federated Learning","papers":5},{"task":"/task/benchmarking","name":"Benchmarking","papers":4},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":4},{"task":"/task/edge-computing","name":"Edge-computing","papers":4}],"tasks_shown":20,"n_tasks":88,"usage_by_year":[{"year":"2015","papers":1},{"year":"2016","papers":1},{"year":"2017","papers":6},{"year":"2018","papers":21},{"year":"2019","papers":22},{"year":"2020","papers":34},{"year":"2021","papers":31},{"year":"2022","papers":32},{"year":"2023","papers":33},{"year":"2024","papers":26},{"year":"2025","papers":11}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/ddpg"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=DDPG","read_at":"2026-10-05T00:54:32+00:00","query":"DDPG","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1509.02971","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'DDPG' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["GAN-DDPG","Soft DDPG","Hawkes-CT DDPG","DDPG framework","Domain Knowledge-Informed DDPG (DKDDPG)","Average Reward Off-Policy Deep Deterministic Policy Gradient (ARO-DDPG) Algorithm"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"5bbbb60b3a6f8c6fde9dc17bd483e37ca525c6ade95ff5105ab0bd7c055faeaa","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}