# Open-World Reinforcement Learning over Long Short-Term Imagination

arXiv: https://arxiv.org/abs/2410.03618 · HTML: https://mlsanity.com/paper/2410.03618/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 50 of its 53 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 50)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [Diffusion for World Modeling: Visual Details Matter in Atari](https://mlsanity.com/paper/2405.12399/) (2024)
- [Decoupling Representation Learning from Reinforcement Learning](https://mlsanity.com/paper/2009.08319/) (2020)
- [Masked Visual Pre-training for Motor Control](https://mlsanity.com/paper/2203.06173/) (2022)
- [Affordances from Human Videos as a Versatile Representation for Robotics](https://mlsanity.com/paper/2304.08488/) (2023)
- [Where2Act: From Pixels to Actions for Articulated 3D Objects](https://mlsanity.com/paper/2101.02692/) (2021)
- [ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2312.16217/) (2023)
- [The Unsurprising Effectiveness of Pre-Trained Vision Models for Control](https://mlsanity.com/paper/2203.03580/) (2022)
- [Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations](https://mlsanity.com/paper/2104.01542/) (2021)
- [Reinforcement Learning with Action-Free Pre-Training from Videos](https://mlsanity.com/paper/2203.13880/) (2022)
- [Pretraining Representations for Data-Efficient Reinforcement Learning](https://mlsanity.com/paper/2106.04799/) (2021)
- [Deep Hierarchical Planning from Pixels](https://mlsanity.com/paper/2206.04114/) (2022)
- [STEVE-1: A Generative Model for Text-to-Behavior in Minecraft](https://mlsanity.com/paper/2306.00937/) (2023)
- [STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning](https://mlsanity.com/paper/2310.09615/) (2023)
- [Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling](https://mlsanity.com/paper/2301.12050/) (2023)
- [FlingBot: The Unreasonable Effectiveness of Dynamic Manipulation for Cloth Unfolding](https://mlsanity.com/paper/2105.03655/) (2021)

## Built on by (most cited first, 13 of 13)

- [SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents](https://mlsanity.com/paper/2506.21669/) (2025)
- [OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability](https://mlsanity.com/paper/2511.20766/) (2025)
- [DMWM: Dual-Mind World Model with Long-Term Imagination](https://mlsanity.com/paper/2502.07591/) (2025)
- [Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning](https://mlsanity.com/paper/2503.08751/) (2025)
- [TRAP: Tail-aware Ranking Attack for World-Model Planning](https://mlsanity.com/paper/2605.01950/) (2026)
- [Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents](https://mlsanity.com/paper/2507.23698/) (2025)
- [ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games](https://mlsanity.com/paper/2607.26712/) (2026)
- [A Data-Driven Discretized CS:GO Simulation Environment to Facilitate Strategic Multi-Agent Planning Research](https://mlsanity.com/paper/2509.06355/) (2025)
- [SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning](https://mlsanity.com/paper/2602.03201/) (2026)
- [OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence](https://mlsanity.com/paper/2605.16395/) (2026)
- [Self-supervised Hierarchical Visual Reasoning with World Model](https://mlsanity.com/paper/2605.17537/) (2026)
- [Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL](https://mlsanity.com/paper/2607.16204/) (2026)
- [Decoupling Planning and Control for Instructable Agents](https://mlsanity.com/paper/2608.26788/) (2026)

## Abstract (arXiv)

Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by learning interactive world models, these agents tend to be "short-sighted", as they are typically trained on short snippets of imagined experiences. We argue that the primary challenge in open-world decision-making is improving the exploration efficiency across a vast state space, especially for tasks that demand consideration of long-horizon payoffs. In this paper, we present LS-Imagine, which extends the imagination horizon within a limited number of state transition steps, enabling the agent to explore behaviors that potentially lead to promising long-term feedback. The foundation of our approach is to build a textitlong short-term world model. To achieve this, we simulate goal-conditioned jumpy state transitions and compute corresponding affordance maps by zooming in on specific areas within single images. This facilitates the integration of direct long-term values into behavior learning. Our method demonstrates significant improvements over state-of-the-art techniques in MineDojo.