mlsanityData to 7 Oct 2026

Offline RL and imitation learning from data

13 directions · 3,787 papers · 19 this week

Busiest this week

Most new since Mon 5 Oct

Robot manipulation imitation learning

737 papers11 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

  1. RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input
  2. Targeted Modality Dropout for Real-Robot Manipulation Robust to Intermittent Vision Loss
  3. Contact-Aware Imitation Learning Through Contact Factorization
  4. Fast Non-Parametric Heteroscedastic Imitation Learning With Geometric Priors
  5. BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation
Open →

All directions

Largest first · week from Mon 5 Oct

  1. Offline RL algorithmsoffline, policy, reinforcement learning, reinforcementHigh confidence in this grouping: the papers form one clear topic · About8191High confidence in this grouping: the papers form one clear topic
  2. Imitation learning methodsimitation, imitation learning, expert, demonstrationsHigh confidence in this grouping: the papers form one clear topic · About7461High confidence in this grouping: the papers form one clear topic
  3. Robot manipulation imitation learningmanipulation, imitation, imitation learning, robotHigh confidence in this grouping: the papers form one clear topic · About73711High confidence in this grouping: the papers form one clear topic
  4. Inverse reinforcement learningreward, inverse, irl, inverse reinforcementHigh confidence in this grouping: the papers form one clear topic · About3211High confidence in this grouping: the papers form one clear topic
  5. Imitation and offline RL for drivingdriving, autonomous, autonomous driving, imitationHigh confidence in this grouping: the papers form one clear topic · About2260High confidence in this grouping: the papers form one clear topic
  6. Decision transformers and sequence modelingdecision, transformer, offline, decision transformerMedium confidence in this grouping: mostly one topic, with blurry edges · About2050Medium confidence in this grouping: mostly one topic, with blurry edges
  7. Language-conditioned policies and VLAslanguage, vla, failure, imitationLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1620Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  8. Diffusion and flow policies for offline RLdiffusion, offline, policy, reinforcement learningMedium confidence in this grouping: mostly one topic, with blurry edges · About1553Medium confidence in this grouping: mostly one topic, with blurry edges
  9. Robot learning from demonstrationdemonstration, lfd, demonstrations, learning demonstrationHigh confidence in this grouping: the papers form one clear topic · About1390High confidence in this grouping: the papers form one clear topic
  10. Safe offline RLsafe, safety, offline, policyLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1150Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  11. Real-world robot offline RLrobot, manipulation, reinforcement learning, reinforcementMedium confidence in this grouping: mostly one topic, with blurry edges · About861Medium confidence in this grouping: mostly one topic, with blurry edges
  12. Offline multi-agent RLmulti-agent, marl, offline, offline multi-agentHigh confidence in this grouping: the papers form one clear topic · About590High confidence in this grouping: the papers form one clear topic
  13. Social robot navigationsocial, navigation, social navigation, pedestrianHigh confidence in this grouping: the papers form one clear topic · About170High confidence in this grouping: the papers form one clear topic
1 new this week isn’t in a direction yet
  1. MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration

Weekly activity

Papers per week, 22 Jun – 5 Oct (last week partial)

  1. DirectionConfidencepapers16 wks
  2. Robot manipulation imitation learningHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 9; 29 Jun: 3; 6 Jul: 9; 13 Jul: 3; 20 Jul: 3; 27 Jul: 8; 3 Aug: 4; 10 Aug: 1; 17 Aug: 5; 24 Aug: 1; 31 Aug: 2; 7 Sep: 6; 14 Sep: 8; 21 Sep: 8; 28 Sep: 8; 5 Oct: 1173789
  3. Diffusion and flow policies for offline RLMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 22 Jun: 1; 29 Jun: 0; 6 Jul: 1; 13 Jul: 0; 20 Jul: 2; 27 Jul: 0; 3 Aug: 1; 10 Aug: 0; 17 Aug: 0; 24 Aug: 3; 31 Aug: 1; 7 Sep: 2; 14 Sep: 2; 21 Sep: 3; 28 Sep: 6; 5 Oct: 315525
  4. Offline RL algorithmsHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 1; 29 Jun: 2; 6 Jul: 2; 13 Jul: 3; 20 Jul: 3; 27 Jul: 2; 3 Aug: 2; 10 Aug: 2; 17 Aug: 2; 24 Aug: 3; 31 Aug: 1; 7 Sep: 4; 14 Sep: 0; 21 Sep: 5; 28 Sep: 4; 5 Oct: 181937
  5. Imitation learning methodsHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 1; 29 Jun: 2; 6 Jul: 2; 13 Jul: 3; 20 Jul: 0; 27 Jul: 1; 3 Aug: 0; 10 Aug: 1; 17 Aug: 2; 24 Aug: 2; 31 Aug: 1; 7 Sep: 0; 14 Sep: 2; 21 Sep: 3; 28 Sep: 4; 5 Oct: 174625
  6. Language-conditioned policies and VLAsLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · AboutLow confidence in this grouping: the papers may belong to more than one topic, or the group may changePer week: 22 Jun: 3; 29 Jun: 3; 6 Jul: 0; 13 Jul: 2; 20 Jul: 0; 27 Jul: 4; 3 Aug: 0; 10 Aug: 0; 17 Aug: 1; 24 Aug: 0; 31 Aug: 2; 7 Sep: 0; 14 Sep: 1; 21 Sep: 1; 28 Sep: 4; 5 Oct: 016221
  7. Decision transformers and sequence modelingMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 22 Jun: 0; 29 Jun: 1; 6 Jul: 0; 13 Jul: 0; 20 Jul: 0; 27 Jul: 0; 3 Aug: 0; 10 Aug: 0; 17 Aug: 0; 24 Aug: 2; 31 Aug: 0; 7 Sep: 0; 14 Sep: 1; 21 Sep: 2; 28 Sep: 2; 5 Oct: 02058
  8. Inverse reinforcement learningHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 1; 29 Jun: 0; 6 Jul: 1; 13 Jul: 1; 20 Jul: 2; 27 Jul: 0; 3 Aug: 1; 10 Aug: 2; 17 Aug: 1; 24 Aug: 0; 31 Aug: 1; 7 Sep: 0; 14 Sep: 0; 21 Sep: 1; 28 Sep: 2; 5 Oct: 132114
  9. Imitation and offline RL for drivingHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 0; 29 Jun: 0; 6 Jul: 0; 13 Jul: 0; 20 Jul: 0; 27 Jul: 0; 3 Aug: 1; 10 Aug: 0; 17 Aug: 1; 24 Aug: 1; 31 Aug: 2; 7 Sep: 0; 14 Sep: 3; 21 Sep: 0; 28 Sep: 1; 5 Oct: 02269
  10. Real-world robot offline RLMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 22 Jun: 0; 29 Jun: 0; 6 Jul: 0; 13 Jul: 0; 20 Jul: 0; 27 Jul: 0; 3 Aug: 0; 10 Aug: 1; 17 Aug: 1; 24 Aug: 0; 31 Aug: 1; 7 Sep: 0; 14 Sep: 1; 21 Sep: 0; 28 Sep: 1; 5 Oct: 1866
  11. Offline multi-agent RLHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 0; 29 Jun: 0; 6 Jul: 0; 13 Jul: 0; 20 Jul: 0; 27 Jul: 0; 3 Aug: 0; 10 Aug: 0; 17 Aug: 0; 24 Aug: 1; 31 Aug: 3; 7 Sep: 0; 14 Sep: 0; 21 Sep: 1; 28 Sep: 1; 5 Oct: 0596
  12. Robot learning from demonstrationHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 0; 29 Jun: 1; 6 Jul: 0; 13 Jul: 2; 20 Jul: 0; 27 Jul: 0; 3 Aug: 1; 10 Aug: 0; 17 Aug: 0; 24 Aug: 1; 31 Aug: 0; 7 Sep: 0; 14 Sep: 0; 21 Sep: 1; 28 Sep: 0; 5 Oct: 01396
  13. Safe offline RLLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · AboutLow confidence in this grouping: the papers may belong to more than one topic, or the group may changePer week: 22 Jun: 0; 29 Jun: 1; 6 Jul: 0; 13 Jul: 1; 20 Jul: 0; 27 Jul: 0; 3 Aug: 1; 10 Aug: 2; 17 Aug: 2; 24 Aug: 0; 31 Aug: 1; 7 Sep: 1; 14 Sep: 0; 21 Sep: 1; 28 Sep: 0; 5 Oct: 011510
  14. Social robot navigationHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 22 Jun: 0; 29 Jun: 1; 6 Jul: 0; 13 Jul: 0; 20 Jul: 0; 27 Jul: 0; 3 Aug: 0; 10 Aug: 0; 17 Aug: 0; 24 Aug: 1; 31 Aug: 0; 7 Sep: 0; 14 Sep: 0; 21 Sep: 0; 28 Sep: 0; 5 Oct: 0172