# Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

arXiv: https://arxiv.org/abs/2110.05038 · HTML: https://mlsanity.com/paper/2110.05038/

## Key facts

- Cited by 122 papers in the map (data through 14 Oct 2026).
- Builds on 79 of its 137 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 30 of 79)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [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)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)

## Built on by (most cited first, 30 of 122)

- [In-context Reinforcement Learning with Algorithm Distillation](https://mlsanity.com/paper/2210.14215/) (2022)
- [Structured State Space Models for In-Context Reinforcement Learning](https://mlsanity.com/paper/2303.03982/) (2023)
- [Large Language Models as Generalizable Policies for Embodied Tasks](https://mlsanity.com/paper/2310.17722/) (2023)
- [Dense Reward for Free in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2402.00782/) (2024)
- [When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment](https://mlsanity.com/paper/2307.03864/) (2023)
- [POPGym: Benchmarking Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2303.01859/) (2023)
- [Bridging State and History Representations: Understanding Self-Predictive RL](https://mlsanity.com/paper/2401.08898/) (2024)
- [AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents](https://mlsanity.com/paper/2310.09971/) (2023)
- [Deep Transformer Q-Networks for Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2206.01078/) (2022)
- [Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning](https://mlsanity.com/paper/2502.10550/) (2025)
- [Learning in Observable POMDPs, without Computationally Intractable Oracles](https://mlsanity.com/paper/2206.03446/) (2022)
- [AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention](https://mlsanity.com/paper/2511.18960/) (2025)
- [Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond](https://mlsanity.com/paper/2310.06147/) (2023)
- [Leveraging Fully Observable Policies for Learning under Partial Observability](https://mlsanity.com/paper/2211.01991/) (2022)
- [Equivariant Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2408.14336/) (2024)
- [TGRL: An Algorithm for Teacher Guided Reinforcement Learning](https://mlsanity.com/paper/2307.03186/) (2023)
- [Recurrent Hypernetworks are Surprisingly Strong in Meta-RL](https://mlsanity.com/paper/2309.14970/) (2023)
- [Diffusion Spectral Representation for Reinforcement Learning](https://mlsanity.com/paper/2406.16121/) (2024)
- [AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers](https://mlsanity.com/paper/2411.11188/) (2024)
- [MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning](https://mlsanity.com/paper/2403.09859/) (2024)
- [Normalizing Flows are Capable Models for Continuous Control](https://mlsanity.com/paper/2505.23527/) (2025)
- [Do Transformer World Models Give Better Policy Gradients?](https://mlsanity.com/paper/2402.05290/) (2024)
- [Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate](https://mlsanity.com/paper/2405.15384/) (2024)
- [Real-Time Recurrent Learning using Trace Units in Reinforcement Learning](https://mlsanity.com/paper/2409.01449/) (2024)
- [AssistanceZero: Scalably Solving Assistance Games](https://mlsanity.com/paper/2504.07091/) (2025)
- [ContraBAR: Contrastive Bayes-Adaptive Deep RL](https://mlsanity.com/paper/2306.02418/) (2023)
- [Reinforcement Learning with Fast and Forgetful Memory](https://mlsanity.com/paper/2310.04128/) (2023)
- [Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples](https://mlsanity.com/paper/2310.07747/) (2023)
- [Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist](https://mlsanity.com/paper/2402.18002/) (2024)
- [Rethinking Transformers in Solving POMDPs](https://mlsanity.com/paper/2405.17358/) (2024)

## Abstract (arXiv)

Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with memory-based architectures, such as recurrent neural networks, provides a general approach to solving all types of POMDPs. However, prior work has found that such recurrent model-free RL methods tend to perform worse than more specialized algorithms that are designed for specific types of POMDPs. This paper revisits this claim. We find that careful architecture and hyperparameter decisions can often yield a recurrent model-free implementation that performs on par with (and occasionally substantially better than) more sophisticated recent techniques. We compare to 21 environments from 6 prior specialized methods and find that our implementation achieves greater sample efficiency and asymptotic performance than these methods on 18/21 environments. We also release a simple and efficient implementation of recurrent model-free RL for future work to use as a baseline for POMDPs.