# RLBenchNet: The Right Network for the Right Reinforcement Learning Task

arXiv: https://arxiv.org/abs/2505.15040 · HTML: https://mlsanity.com/paper/2505.15040/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)
- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study](https://mlsanity.com/paper/2006.05990/) (2020)
- [When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment](https://mlsanity.com/paper/2307.03864/) (2023)
- [Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2403.19925/) (2024)
- [Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents](https://mlsanity.com/paper/2309.17207/) (2023)
- [Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL](https://mlsanity.com/paper/2406.05427/) (2024)
- [Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate](https://mlsanity.com/paper/2405.15384/) (2024)
- [Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2405.16390/) (2024)

## Built on by (most cited first, 2 of 2)

- [When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift](https://mlsanity.com/paper/2603.04648/) (2026)
- [Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning](https://mlsanity.com/paper/2608.05111/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) has seen significant advancements through the application of various neural network architectures. In this study, we systematically investigate the performance of several neural networks in RL tasks, including Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), Mamba/Mamba-2, Transformer-XL, Gated Transformer-XL, and Gated Recurrent Unit (GRU). Through comprehensive evaluation across continuous control, discrete decision-making, and memory-based environments, we identify architecture-specific strengths and limitations. Our results reveal that: (1) MLPs excel in fully observable continuous control tasks, providing an optimal balance of performance and efficiency; (2) recurrent architectures like LSTM and GRU offer robust performance in partially observable environments with moderate memory requirements; (3) Mamba models achieve a 4.5x higher throughput compared to LSTM and a 3.9x increase over GRU, all while maintaining comparable performance; and (4) only Transformer-XL, Gated Transformer-XL, and Mamba-2 successfully solve the most challenging memory-intensive tasks, with Mamba-2 requiring 8x less memory than Transformer-XL. These findings provide insights for researchers and practitioners, enabling more informed architecture selection based on specific task characteristics and computational constraints. Code is available at: https://github.com/SafeRL-Lab/RLBenchNet