# Investigating Memory in Model-Free RL with POPGym Arcade

arXiv: https://arxiv.org/abs/2503.01450 · HTML: https://mlsanity.com/paper/2503.01450/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 41 of its 63 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Placed in

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

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Resurrecting Recurrent Neural Networks for Long Sequences](https://mlsanity.com/paper/2303.06349/) (2023)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [Stabilizing Transformers for Reinforcement Learning](https://mlsanity.com/paper/1910.06764/) (2019)
- [The Illusion of State in State-Space Models](https://mlsanity.com/paper/2404.08819/) (2024)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs](https://mlsanity.com/paper/2110.05038/) (2021)
- [Structured State Space Models for In-Context Reinforcement Learning](https://mlsanity.com/paper/2303.03982/) (2023)
- [Discovered Policy Optimisation](https://mlsanity.com/paper/2210.05639/) (2022)
- [The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels](https://mlsanity.com/paper/2101.02722/) (2021)
- [When Is Partially Observable Reinforcement Learning Not Scary?](https://mlsanity.com/paper/2204.08967/) (2022)
- [Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning](https://mlsanity.com/paper/2402.16801/) (2024)
- [Simplifying Deep Temporal Difference Learning](https://mlsanity.com/paper/2407.04811/) (2024)
- [On the difficulty of learning chaotic dynamics with RNNs](https://mlsanity.com/paper/2110.07238/) (2021)
- [When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment](https://mlsanity.com/paper/2307.03864/) (2023)
- [EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine](https://mlsanity.com/paper/2206.10558/) (2022)
- [Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX](https://mlsanity.com/paper/2306.09884/) (2023)
- [Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning](https://mlsanity.com/paper/2303.17503/) (2023)

## Built on by (most cited first, 3 of 3)

- [In-Context Reinforcement Learning under Non-Stationarity: A Survey](https://mlsanity.com/paper/2607.11906/) (2026)
- [ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning](https://mlsanity.com/paper/2610.00592/) (2026)
- [Does Learning Recurrent Networks Matter in Partially Observable RL?](https://mlsanity.com/paper/2610.13197/) (2026)

## Abstract (arXiv)

How should we analyze memory in deep RL? We introduce tools for analyzing policies under partial observability and revealing how agents use memory to make decisions. To utilize these tools, we present POPGym Arcade, a collection of Atari-inspired, hardware-accelerated environments sharing a single observation and action space. Each environment provides fully and partially observable variants, enabling counterfactual studies on observability. We find that controlled studies are necessary for fair comparisons and identify a pathology where value functions smear credit over irrelevant history. Using this pathology, we demonstrate how out-of-distribution scenarios can contaminate memory, perturbing the policy far into the future. Our code is available at https://github.com/bolt-research/popgym-arcade.