mlsanityData to 14 Oct 2026

Task-Space Imitation Guidance for Efficient Reinforcement Learning

arXiv 2610.07527 ↗First posted 5 Oct 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

We introduce Task-Space Imitation Guidance for Efficient Reinforcement Learning (TIGER), a reward-construction and pretraining framework for sparse-reward tabletop robotic manipulation. TIGER treats an action-chunked imitation policy not as an executable controller or action prior, but as a local task-space progress estimator: predicted action chunks are converted, using controller-aware action-to-motion mapping, into short-horizon end-effector references, and the RL agent receives dense progress rewards toward these references while the sparse environment reward remains the dominant objective. During pretraining, TIGER uses imitation-guided look-ahead signals to relax conservative value penalties for actions predicted to make task-space progress, reducing off-manifold exploration during early online RL. Across simulation and real-robot experiments, TIGER improves early sample efficiency and reduces measured safety violations while matching or improving final success rates relative to prior RL and IL-RL baselines on the evaluated tasks. Videos and an overview of this work are available at https://sanctuary.ai/news/tiger/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 32 of its 37 references that are in the map. First posted on arXiv 5 Oct 2026.

Builds on

32 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learning18 Jun
  2. 2024Rank2Reward: Learning Shaped Reward Functions from Passive Video23 Apr
  3. 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning29 Jan

Other references · 29

  1. 2022Flow Matching for Generative Modelingcited by 5,702
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  3. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,920
  5. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  6. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  7. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  8. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,293
  9. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  10. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  11. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
  12. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 671
17 more
  1. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  2. 2023Efficient Online Reinforcement Learning with Offline Datacited by 363
  3. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 319
  4. 2023Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuningcited by 237
  5. 2022CORL: Research-oriented Deep Offline Reinforcement Learning Librarycited by 119
  6. 2018Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Costcited by 84
  7. 2024Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbonecited by 79
  8. 2021A Workflow for Offline Model-Free Robotic Reinforcement Learningcited by 69
  9. 2022Watch and Match: Supercharging Imitation with Regularized Optimal Transportcited by 67
  10. 2023Imitation Bootstrapped Reinforcement Learningcited by 64
  11. 2025ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrationscited by 60
  12. 2026Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisonscited by 60
  13. 2025Residual Off-Policy RL for Finetuning Behavior Cloning Policiescited by 55
  14. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 38
  15. 2022On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrationscited by 19
  16. 2022Learning to Brachiate via Simplified Model Imitationcited by 9
  17. 2025When a Robot is More Capable than a Human: Learning from Constrained Demonstratorscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
  2. 2021Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning
  3. 2019Reinforced Imitation in Heterogeneous Action Space
  4. 2025Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
  5. 2026Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models
  6. 2026TRACT: Temporally Routed Action Chunks with Chronological Phase Authority for Contact-Rich Manipulation
  7. 2022Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks
  8. 2022STIR2: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks