No article text was recorded for this version.
residual policy learning (residual reinforcement learning)
Version 1 of 167 papers83 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Touch begins where vision ends: Generalizable policies for contact-rich manipulation
- Blog: Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
- Blog: Residual learning and context encoding for adaptive offline-to-online reinforcement learning
- Blog: Learning Vision-based Reactive Policies for Obstacle Avoidance
- Blog: RESPRECT: Speeding-up Multi-fingered Grasping with Residual Reinforcement Learning
- Blog: Dejavu: Post-Deployment Learning for Embodied Agents via Experience Feedback
- Blog: REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
- Blog: Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
- Blog: Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
- Blog: Drive Fast, Learn Faster: On-Board RL for High Performance Autonomous Racing
- Blog: Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
- Blog: Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations
- Blog: DyGRO-VLA: Cross-Task Scaling of Vision–Language–Action Models via Dynamic Grouped Residual Optimization
- Blog: HandelBot: Real-World Piano Playing via Fast Adaptation of Dexterous Robot Policies
- Blog: Self-Composing Policies for Scalable Continual Reinforcement Learning
- Blog: TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction
- Blog: EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- Blog: Residual Off-Policy RL for Finetuning Behavior Cloning Policies
- Blog: Accelarating Imitation Learning in Relational Domains via Transfer by Initialization
- Blog: Focus-Then-Contact: Speeding Up Robotic Contact-Rich Task Learning with Affordance-Guided Real-World Residual Reinforcement Learning
- Blog: Multi-residual Mixture of Experts Learning for Cooperative Control in Multi-vehicle Systems
- Blog: ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning
- Blog: CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
- Blog: Self-Composing Policies for Scalable Continual Reinforcement Learning
- Blog: Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving
- Blog: Residual Robot Learning for Object-Centric Probabilistic Movement Primitives
- Blog: The State of Reinforcement Finetuning for Transformer-based Agents
- Blog: Track2Act: Predicting Point Tracks from Internet Videos Enables Generalizable Robot Manipulation
- Blog: Leave No Observation Behind: Real-time Correction for VLA Action Chunks
- Blog: AdaptNet: Policy Adaptation for Physics-Based Character Control
- Blog: What Makes Value Learning Efficient in Residual Reinforcement Learning?
- Blog: Bayesian Residual Policy Optimization: : Scalable Bayesian Reinforcement Learning with Clairvoyant Experts
- Blog: Model Based Residual Policy Learning with Applications to Antenna Control
- Blog: Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
- Blog: Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
- Blog: PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems
- Blog: Learning Terrain-Adaptive Locomotion with Agile Behaviors by Imitating Animals
- Blog: Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark
- Blog: ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning
- Blog: Utility Decomposition with Deep Corrections for Scalable Planning under Uncertainty
- Blog: HuDOR: Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards
- Blog: ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
- Blog: Robust Driving Across Scenarios via Multi-residual Task Learning
- Blog: Reinforcement Learning Experience Reuse with Policy Residual Representation
- Blog: DEFT: Dexterous Fine-Tuning for Hand Policies
- Blog: ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning
- Blog: Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
- Blog: Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics
- Blog: Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections
- Blog: SPAR: Support-Preserving Action Rectification
- Blog: MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation
- Blog: Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics
- Blog: EXPO: Stable Reinforcement Learning with Expressive Policies
- Blog: MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics
- Blog: WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
- Blog: Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
- Blog: Re:Frame - Retrieving Experience From Associative Memory
- Blog: Combining Learning from Demonstration with Learning by Exploration to Facilitate Contact-Rich Tasks
- Blog: From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
- Blog: Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks
Showing 60 of 67 papers.
History & citation
Current · Permanent link
- Residual Reinforcement Learning for Policy Refinement merged into this direction (52% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_residual_policy_learning_residual_reinfo_3d1066fd,
title = {residual policy learning (residual reinforcement learning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/residual-policy-learning-residual-reinforcement-learning/rdr_3d1066fdc6424fca8088027eb292d0d7},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_residual_policy_learning_residual_reinfo_3d1066fd_v1,
title = {residual policy learning (residual reinforcement learning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/residual-policy-learning-residual-reinforcement-learning/rdr_3d1066fdc6424fca8088027eb292d0d7/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}