# Deep RL algorithms and representations

Area: [Deep reinforcement learning methods](https://mlsanity.com/deeprl/index.md). HTML: https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/

## 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).
- 36 of its 1,402 mapped papers (3%) cite “Stop Regressing: Training Value Functions via Classification for Scalable Deep RL” (2024, arXiv 2403.03950).
- 47 new papers 30 Sep–14 Oct.

## Most cited here

- [Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control](https://mlsanity.com/paper/2405.16158/) (2024), cited by 48 papers here
- [Stop Regressing: Training Value Functions via Classification for Scalable Deep RL](https://mlsanity.com/paper/2403.03950/) (2024), cited by 36 papers here
- [Disentangling the Causes of Plasticity Loss in Neural Networks](https://mlsanity.com/paper/2402.18762/) (2024), cited by 35 papers here
- [SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.09754/) (2024), cited by 35 papers here
- [Mixtures of Experts Unlock Parameter Scaling for Deep RL](https://mlsanity.com/paper/2402.08609/) (2024), cited by 34 papers here
- [Foundation Policies with Hilbert Representations](https://mlsanity.com/paper/2402.15567/) (2024), cited by 33 papers here
- [Simplifying Deep Temporal Difference Learning](https://mlsanity.com/paper/2407.04811/) (2024), cited by 32 papers here
- [In value-based deep reinforcement learning, a pruned network is a good network](https://mlsanity.com/paper/2402.12479/) (2024), cited by 24 papers here
- [Normalization and effective learning rates in reinforcement learning](https://mlsanity.com/paper/2407.01800/) (2024), cited by 24 papers here
- [Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making](https://mlsanity.com/paper/2406.17098/) (2024), cited by 23 papers here

## New (30 Sep–14 Oct)

- [Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning](https://mlsanity.com/paper/2610.20463/) (2026-10-14)
- [Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL](https://mlsanity.com/paper/2610.20009/) (2026-10-14)
- [Provable Transformer Context Compression for In-Context Reinforcement Learning](https://mlsanity.com/paper/2610.20004/) (2026-10-14)
- [Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction](https://mlsanity.com/paper/2610.19883/) (2026-10-14)
- [Reinforcement Learning via Advantage Guidance](https://mlsanity.com/paper/2610.19783/) (2026-10-14)
- [MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces](https://mlsanity.com/paper/2610.19457/) (2026-10-14)
- [When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2610.18229/) (2026-10-13)
- [From Policy Evaluation to Off-Policy Control: Provable Emergence of In-Context Q-Learning](https://mlsanity.com/paper/2610.18057/) (2026-10-13)
- [FARL: A Fully Automated Pipeline of RL Interface and Solver Design](https://mlsanity.com/paper/2610.15691/) (2026-10-11)
- [PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents](https://mlsanity.com/paper/2610.14636/) (2026-10-10)
- [Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations](https://mlsanity.com/paper/2610.14400/) (2026-10-09)
- [Does Learning Recurrent Networks Matter in Partially Observable RL?](https://mlsanity.com/paper/2610.13197/) (2026-10-09)
- [Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target](https://mlsanity.com/paper/2610.12830/) (2026-10-09)
- [Q-Shaped Options for Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2610.12135/) (2026-10-08)
- [World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2610.10932/) (2026-10-07)
- [Sample-Efficiency of Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2610.10627/) (2026-10-07)
- [A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching](https://mlsanity.com/paper/2610.10447/) (2026-10-07)
- [CERO: Where and When to Allocate Rollouts for RL Post-Training](https://mlsanity.com/paper/2610.09679/) (2026-10-07)
- [An Informational Curse of Horizon in Goal-Conditioned Policy Learning](https://mlsanity.com/paper/2610.09247/) (2026-10-07)
- [Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning](https://mlsanity.com/paper/2610.07910/) (2026-10-06)
- [AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints](https://mlsanity.com/paper/2610.07615/) (2026-10-06)
- [Considering Context: When World Models Need Context Encoders](https://mlsanity.com/paper/2610.06651/) (2026-10-05)
- [Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning](https://mlsanity.com/paper/2610.06244/) (2026-10-05)
- [Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning](https://mlsanity.com/paper/2610.06019/) (2026-10-05)
- [Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning](https://mlsanity.com/paper/2610.05446/) (2026-10-04)
- [On Semi-Markov Suboptimality in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2610.05338/) (2026-10-04)
- [Arithmetic Actor Heads and Training Stabilization for Out-of-Distribution Reinforcement Learning](https://mlsanity.com/paper/2610.05143/) (2026-10-04)
- [Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2610.05087/) (2026-10-04)
- [UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning](https://mlsanity.com/paper/2610.03620/) (2026-10-02)
- [Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learning](https://mlsanity.com/paper/2610.03395/) (2026-10-02)