mlsanityData to 14 Oct 2026

Deep RL algorithms and representations

1,402 papers8 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: reinforcement learning, reinforcement, performance, policy, environments

Key facts. Deep RL algorithms and representations: 1,402 papers on arXiv since 2024 (data through 14 Oct 2026). 48 of its 1,402 mapped papers (3%) cite “Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control” (2024, arXiv 2405.16158). 47 new papers 30 Sep–14 Oct.

What’s new

30 Sep – 14 Oct 2026

47 new papers, 30 Sep – 14 Oct; 8 this week.

  1. This week · 8
  2. Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning also fits: RL theory and sample complexity
  3. Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL also fits: RL with diffusion and flow models
  4. Provable Transformer Context Compression for In-Context Reinforcement Learning also fits: RL theory and sample complexity
  5. Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction also fits: RL with diffusion and flow models
  6. Reinforcement Learning via Advantage Guidance
  7. MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces also fits: RL theory and sample complexity
  8. When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability also fits: RL for games and combinatorial optimization
  9. From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning also fits: RL theory and sample complexity
  10. Earlier · 39
  11. FARL: A Fully Automated Pipeline of RL Interface and Solver Design also fits: RL for robot locomotion and manipulation
  12. PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents
All 47
  1. Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations
  2. Does Learning Recurrent Networks Matter in Partially Observable RL?
  3. Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target also fits: RL training of language and agent models
  4. Q-Shaped Options for Hierarchical Reinforcement Learning also fits: Interpretable and logic-guided RL
  5. World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning also fits: RL theory and sample complexity
  6. Sample-Efficiency of Kolmogorov-Arnold Networks also fits: RL theory and sample complexity
  7. A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching also fits: RL training of language and agent models
  8. CERO: Where and When to Allocate Rollouts for RL Post-Training also fits: RL training of language and agent models
  9. An Informational Curse of Horizon in Goal-Conditioned Policy Learning
  10. Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning also fits: RL with diffusion and flow models
  11. AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints also fits: RL theory and sample complexity
  12. Considering Context: When World Models Need Context Encoders
  13. Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning also fits: RL with diffusion and flow models
  14. Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning also fits: RL for games and combinatorial optimization
  15. Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning
  16. On Semi-Markov Suboptimality in Hierarchical Reinforcement Learning also fits: RL theory and sample complexity
  17. Arithmetic Actor Heads and Training Stabilization for Out-of-Distribution Reinforcement Learning also fits: RL theory and sample complexity
  18. Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning also fits: RL for robot locomotion and manipulation
  19. UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning also fits: RL for robot locomotion and manipulation
  20. Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learning also fits: RL for robot locomotion and manipulation
  21. How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
  22. Understanding Enrichment in Reinforcement Learning also fits: RL training of language and agent models
  23. Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
  24. Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation also fits: RL training of language and agent models
  25. Reward Inflation: A Healthy Stimulus for Reinforcement Learning
  26. When Do Intrinsic Rewards Lead to Exploration?
  27. Finetuning with Sampling: SFT Learns Better Than You Think also fits: RL with diffusion and flow models
  28. Continual Reinforcement Learning with Neuroevolution
  29. Optimal Transport Meets Reinforcement Learning: A Survey also fits: RL theory and sample complexity
  30. Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help? also fits: RL theory and sample complexity
  31. Does Scaling Reinforcement Learning Really Require More Training? also fits: RL training of language and agent models
  32. Calibration-risk routing for controlled world-model adaptation also fits: RL for robot locomotion and manipulation
  33. Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning
  34. Scalable Multi-Task Inverse Reinforcement Learning
  35. ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning also fits: RL training of language and agent models
  36. Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?
  37. Belief-Based Maximum Occupancy Principle and Active Inference also fits: RL theory and sample complexity

Foundations

Most cited by papers here

  1. Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control2024cited by 48 here
  2. Stop Regressing: Training Value Functions via Classification for Scalable Deep RL2024cited by 36 here
  3. Disentangling the Causes of Plasticity Loss in Neural Networks2024cited by 35 here
  4. SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning2024cited by 35 here
  5. Mixtures of Experts Unlock Parameter Scaling for Deep RL2024cited by 34 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2024Mixtures of Experts Unlock Parameter Scaling for Deep RLcited by 34 here
  2. 2024In value-based deep reinforcement learning, a pruned network is a good networkcited by 24 here
  3. 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RLcited by 36 here
  4. 2024Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous controlcited by 48 here
  5. 2024Simplifying Deep Temporal Difference Learningcited by 32 here
  6. 2024SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learningcited by 35 here
  7. 2025Flow Q-Learningcited by 16 here
  8. 2025Horizon Reduction Makes RL Scalablecited by 21 here
16 more it builds on, not in this chain
  1. 2024Bridging State and History Representations: Understanding Self-Predictive RLcited by 20 here
  2. 2024Exploration and Anti-Exploration with Distributional Random Network Distillationcited by 15 here
  3. 2024Foundation Policies with Hilbert Representationscited by 33 here
  4. 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 29 here
  5. 2024Disentangling the Causes of Plasticity Loss in Neural Networkscited by 35 here
  6. 2024Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learningcited by 30 here
  7. 2024EfficientZero V2: Mastering Discrete and Continuous Control with Limited Datacited by 16 here
  8. 2024Reinforcement learningcited by 30 here
  9. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 18 here
  10. 2024Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Makingcited by 23 here
  11. 2024Normalization and effective learning rates in reinforcement learningcited by 24 here
  12. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 85 here
  13. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 17 here
  14. 2025Towards General-Purpose Model-Free Reinforcement Learningcited by 22 here
  15. 2025Hyperspherical Normalization for Scalable Deep Reinforcement Learningcited by 17 here
  16. 20251000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilitiescited by 15 here

The 24 most cited of 902.

Browse

30 of 1,402, ranked 6–35

  1. 6Foundation Policies with Hilbert Representations202433
  2. 7Simplifying Deep Temporal Difference Learning202432
  3. 8In value-based deep reinforcement learning, a pruned network is a good network202424
  4. 9Normalization and effective learning rates in reinforcement learning202424
  5. 10Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making202423
  6. 11Towards General-Purpose Model-Free Reinforcement Learning202522
  7. 12Horizon Reduction Makes RL Scalable202521
  8. 13Bridging State and History Representations: Understanding Self-Predictive RL202420
  9. 14Hyperspherical Normalization for Scalable Deep Reinforcement Learning202517
  10. 15EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data202416
All 30
  1. 161000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities202515
  2. 17Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models202515
  3. 18Exploration and Anti-Exploration with Distributional Random Network Distillation202415
  4. 19Reinforcement Learning with Action Chunking202513
  5. 20Sharing Knowledge in Multi-Task Deep Reinforcement Learning202413
  6. 21A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning202413
  7. 22On the consistency of hyper-parameter selection in value-based deep reinforcement learning202413
  8. 23Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data202413
  9. 24MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization202413
  10. 25Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings202412
  11. 26Streaming Deep Reinforcement Learning Finally Works202412
  12. 27Mastering Memory Tasks with World Models202411
  13. 28Accelerating Goal-Conditioned RL Algorithms and Research202411
  14. 29No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery202411
  15. 30Plasticity Loss in Deep Reinforcement Learning: A Survey202411
  16. 31Proto Successor Measure: Representing the Behavior Space of an RL Agent202410
  17. 32Parseval Regularization for Continual Reinforcement Learning202410
  18. 33Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization20259
  19. 34XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning20259
  20. 35Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces20249