Data to 14 Oct 2026

Divide-and-Conquer Reinforcement Learning

arXiv 1711.09874 ↗First posted 27 Nov 2017cs.LG cs.ROcited by 48

Not on the map. Why?

Abstract (arXiv)

Standard model-free deep reinforcement learning (RL) algorithms sample a new initial state for each trial, allowing them to optimize policies that can perform well even in highly stochastic environments. However, problems that exhibit considerable initial state variation typically produce high-variance gradient estimates for model-free RL, making direct policy or value function optimization challenging. In this paper, we develop a novel algorithm that instead partitions the initial state space into "slices", and optimizes an ensemble of policies, each on a different slice. The ensemble is gradually unified into a single policy that can succeed on the whole state space. This approach, which we term divide-and-conquer RL, is able to solve complex tasks where conventional deep RL methods are ineffective. Our results show that divide-and-conquer RL greatly outperforms conventional policy gradient methods on challenging grasping, manipulation, and locomotion tasks, and exceeds the performance of a variety of prior methods. Videos of policies learned by our algorithm can be viewed at http://bit.ly/dnc-rl

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 9; 2023: 8; 2024: 6; 2025: 6; 2026: 3.

48 papers.

Sort:

By area:

2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 109
2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 107
2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
2023PADL: Language-Directed Physics-Based Character Controlcited by 48
2024RLDG: Robotic Generalist Policy Distillation via Reinforcement Learningcited by 47
2021Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularizationcited by 46
2021Hierarchical Skills for Efficient Explorationcited by 38
2023HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulationcited by 29
2022Learning to Grasp the Ungraspable with Emergent Extrinsic Dexteritycited by 28
2021Specializing Versatile Skill Libraries using Local Mixture of Expertscited by 24

36 more

2023A Survey on Physics Informed Reinforcement Learning: Review and Open Problemscited by 24
2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learnerscited by 23
2022Improving Policy Optimization with Generalist-Specialist Learningcited by 20
2022Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemblecited by 18
2024PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitationcited by 18
2021Hierarchical Neural Dynamic Policiescited by 17
2021Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillationcited by 15
2021Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learningcited by 15
2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
2022Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approachcited by 14
2024Multi-objective Reinforcement learning from AI Feedbackcited by 10
2022Hierarchically Structured Task-Agnostic Continual Learningcited by 9
2023Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robotcited by 9
2021Mixture-of-Variational-Experts for Continual Learningcited by 8
2022Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomizationcited by 8
2021Training Transition Policies via Distribution Matching for Complex Taskscited by 6
2023QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharingcited by 6
2024Task and Domain Adaptive Reinforcement Learning for Robot Controlcited by 4
2023Goal-conditioned Offline Reinforcement Learning through State Space Partitioningcited by 3
2025Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidancecited by 3
2021Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific researchcited by 1
2021Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combatcited by 1
2023A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Taskscited by 1
2025How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learningcited by 1
2021Clustering and attention model based for intelligent tradingcited by 0
2021Towards Autonomous Satellite Communications: An AI-based Framework to Address System-level Challengescited by 0
2022Symbolic Distillation for Learned TCP Congestion Controlcited by 0
2022Improving generalization in reinforcement learning through forked agentscited by 0
2024Shared learning of powertrain control policies for vehicle fleetscited by 0
2024GSL-PCD: Improving Generalist-Specialist Learning with Point Cloud Feature-based Task Partitioningcited by 0
2025Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policycited by 0
2025Prescribe-then-Select: Adaptive Policy Selection for Contextual Stochastic Optimizationcited by 0
2025PrefPoE: Advantage-Guided Preference Fusion for Learning Where to Explorecited by 0
2026Self Paced Gaussian Contextual Reinforcement Learningcited by 0
2026Mesh-RL: Coupled subgrid reinforcement learningcited by 0
2026Single or Multiple Policies for Phase-Structured Reinforcement Learning?cited by 0