mlsanityData to 14 Oct 2026

Deep reinforcement learning methods

15 directions · 8,890 papers · 57 this week

Busiest this week

Most new since Mon 12 Oct

RL training of language and agent models

1,015 papers13 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

  1. C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning
  2. MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learning
  3. Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live?
  4. GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning
  5. PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
Open →

All directions

Largest first · week from Mon 12 Oct

  1. Deep RL algorithms and representationsreinforcement learning, reinforcement, performance, policyLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1,4028Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  2. RL theory and sample complexitypolicy, reinforcement learning, reinforcement, algorithmLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1,3807Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  3. RL for robot locomotion and manipulationreinforcement, reinforcement learning, robot, policyLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1,1088Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  4. RL training of language and agent modelsreinforcement, reinforcement learning, reward, reasoningMedium confidence in this grouping: mostly one topic, with blurry edges · About1,01513Medium confidence in this grouping: mostly one topic, with blurry edges
  5. RL for energy, networks and operationsreinforcement, reinforcement learning, energy, controlLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About8634Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  6. RL for robot navigation and UAV controlnavigation, reinforcement, reinforcement learning, controlLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About6183Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  7. RL for games and combinatorial optimizationreinforcement, reinforcement learning, games, policyLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About5601Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  8. RL for autonomous driving and trafficdriving, traffic, autonomous, controlHigh confidence in this grouping: the papers form one clear topic · About4342High confidence in this grouping: the papers form one clear topic
  9. Adversarial robustness and RL in financemarket, adversarial, reinforcement, reinforcement learningLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About3641Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  10. RL with diffusion and flow modelsdiffusion, flow, policy, reinforcementLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About3466Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  11. Safe and constrained RLsafety, safe, reinforcement, reinforcement learningHigh confidence in this grouping: the papers form one clear topic · About3232High confidence in this grouping: the papers form one clear topic
  12. Interpretable and logic-guided RLreinforcement, reinforcement learning, reward, symbolicLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1950Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  13. Quantum reinforcement learningquantum, circuits, circuit, reinforcementHigh confidence in this grouping: the papers form one clear topic · About1300High confidence in this grouping: the papers form one clear topic
  14. RL for clinical treatment and surgeryclinical, treatment, medical, reinforcementLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About1161Low confidence in this grouping: the papers may belong to more than one topic, or the group may change
  15. Spiking and neuromorphic RLspiking, neuromorphic, snns, spiking neuralHigh confidence in this grouping: the papers form one clear topic · About360High confidence in this grouping: the papers form one clear topic
1 new this week isn’t in a direction yet
  1. Time Window Optimization for Motor Imagery Classification via Temporal Structure Embedded Reinforcement Learning

Weekly activity

Papers per week, 29 Jun – 12 Oct (last week partial)

  1. DirectionConfidencepapers16 wks
  2. RL training of language and agent modelsMedium confidence in this grouping: mostly one topic, with blurry edges · AboutMedium confidence in this grouping: mostly one topic, with blurry edgesPer week: 29 Jun: 4; 6 Jul: 11; 13 Jul: 6; 20 Jul: 8; 27 Jul: 15; 3 Aug: 14; 10 Aug: 9; 17 Aug: 14; 24 Aug: 17; 31 Aug: 11; 7 Sep: 4; 14 Sep: 10; 21 Sep: 19; 28 Sep: 32; 5 Oct: 19; 12 Oct: 131,015206
  3. RL for robot locomotion and manipulationLow 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: 29 Jun: 16; 6 Jul: 3; 13 Jul: 10; 20 Jul: 7; 27 Jul: 9; 3 Aug: 12; 10 Aug: 6; 17 Aug: 13; 24 Aug: 3; 31 Aug: 7; 7 Sep: 11; 14 Sep: 15; 21 Sep: 23; 28 Sep: 17; 5 Oct: 22; 12 Oct: 81,108182
  4. Deep RL algorithms and representationsLow 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: 29 Jun: 12; 6 Jul: 7; 13 Jul: 7; 20 Jul: 14; 27 Jul: 8; 3 Aug: 13; 10 Aug: 4; 17 Aug: 7; 24 Aug: 5; 31 Aug: 9; 7 Sep: 7; 14 Sep: 7; 21 Sep: 10; 28 Sep: 31; 5 Oct: 16; 12 Oct: 81,402165
  5. RL theory and sample complexityLow 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: 29 Jun: 5; 6 Jul: 6; 13 Jul: 10; 20 Jul: 17; 27 Jul: 9; 3 Aug: 9; 10 Aug: 5; 17 Aug: 11; 24 Aug: 6; 31 Aug: 5; 7 Sep: 7; 14 Sep: 10; 21 Sep: 11; 28 Sep: 29; 5 Oct: 14; 12 Oct: 71,380161
  6. RL with diffusion and flow modelsLow 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: 29 Jun: 5; 6 Jul: 3; 13 Jul: 6; 20 Jul: 1; 27 Jul: 2; 3 Aug: 2; 10 Aug: 2; 17 Aug: 0; 24 Aug: 5; 31 Aug: 2; 7 Sep: 1; 14 Sep: 2; 21 Sep: 5; 28 Sep: 6; 5 Oct: 6; 12 Oct: 634654
  7. RL for energy, networks and operationsLow 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: 29 Jun: 5; 6 Jul: 9; 13 Jul: 6; 20 Jul: 2; 27 Jul: 0; 3 Aug: 3; 10 Aug: 6; 17 Aug: 5; 24 Aug: 4; 31 Aug: 9; 7 Sep: 5; 14 Sep: 6; 21 Sep: 3; 28 Sep: 6; 5 Oct: 6; 12 Oct: 486379
  8. RL for robot navigation and UAV controlLow 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: 29 Jun: 14; 6 Jul: 2; 13 Jul: 5; 20 Jul: 4; 27 Jul: 2; 3 Aug: 3; 10 Aug: 5; 17 Aug: 3; 24 Aug: 3; 31 Aug: 3; 7 Sep: 4; 14 Sep: 3; 21 Sep: 5; 28 Sep: 5; 5 Oct: 6; 12 Oct: 361870
  9. Adversarial robustness and RL in financeLow 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: 29 Jun: 5; 6 Jul: 6; 13 Jul: 2; 20 Jul: 0; 27 Jul: 2; 3 Aug: 3; 10 Aug: 2; 17 Aug: 1; 24 Aug: 2; 31 Aug: 1; 7 Sep: 6; 14 Sep: 2; 21 Sep: 7; 28 Sep: 6; 5 Oct: 5; 12 Oct: 136451
  10. Safe and constrained RLHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 29 Jun: 2; 6 Jul: 2; 13 Jul: 7; 20 Jul: 1; 27 Jul: 3; 3 Aug: 1; 10 Aug: 1; 17 Aug: 1; 24 Aug: 5; 31 Aug: 2; 7 Sep: 5; 14 Sep: 3; 21 Sep: 4; 28 Sep: 3; 5 Oct: 5; 12 Oct: 232347
  11. RL for games and combinatorial optimizationLow 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: 29 Jun: 9; 6 Jul: 2; 13 Jul: 4; 20 Jul: 2; 27 Jul: 3; 3 Aug: 6; 10 Aug: 4; 17 Aug: 2; 24 Aug: 2; 31 Aug: 4; 7 Sep: 2; 14 Sep: 3; 21 Sep: 2; 28 Sep: 5; 5 Oct: 5; 12 Oct: 156056
  12. RL for autonomous driving and trafficHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 29 Jun: 5; 6 Jul: 2; 13 Jul: 2; 20 Jul: 4; 27 Jul: 3; 3 Aug: 1; 10 Aug: 8; 17 Aug: 6; 24 Aug: 2; 31 Aug: 4; 7 Sep: 1; 14 Sep: 4; 21 Sep: 0; 28 Sep: 3; 5 Oct: 3; 12 Oct: 243450
  13. Interpretable and logic-guided 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: 29 Jun: 0; 6 Jul: 1; 13 Jul: 5; 20 Jul: 3; 27 Jul: 2; 3 Aug: 3; 10 Aug: 3; 17 Aug: 0; 24 Aug: 0; 31 Aug: 1; 7 Sep: 0; 14 Sep: 1; 21 Sep: 1; 28 Sep: 1; 5 Oct: 3; 12 Oct: 019524
  14. Quantum reinforcement learningHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 29 Jun: 2; 6 Jul: 1; 13 Jul: 1; 20 Jul: 2; 27 Jul: 0; 3 Aug: 1; 10 Aug: 1; 17 Aug: 0; 24 Aug: 0; 31 Aug: 0; 7 Sep: 2; 14 Sep: 2; 21 Sep: 2; 28 Sep: 2; 5 Oct: 0; 12 Oct: 013016
  15. Spiking and neuromorphic RLHigh confidence in this grouping: the papers form one clear topic · AboutHigh confidence in this grouping: the papers form one clear topicPer week: 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: 0; 7 Sep: 0; 14 Sep: 0; 21 Sep: 2; 28 Sep: 1; 5 Oct: 1; 12 Oct: 0365
  16. RL for clinical treatment and surgeryLow 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: 29 Jun: 0; 6 Jul: 1; 13 Jul: 1; 20 Jul: 1; 27 Jul: 0; 3 Aug: 1; 10 Aug: 3; 17 Aug: 0; 24 Aug: 0; 31 Aug: 1; 7 Sep: 2; 14 Sep: 1; 21 Sep: 0; 28 Sep: 2; 5 Oct: 0; 12 Oct: 111614