# Go-Explore: a New Approach for Hard-Exploration Problems

arXiv: https://arxiv.org/abs/1901.10995 · HTML: https://mlsanity.com/paper/1901.10995/

## Key facts

- Cited by 212 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 30 Jan 2019.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Built on by (most cited first, 30 of 212)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [Discovering and Achieving Goals via World Models](https://mlsanity.com/paper/2110.09514/) (2021)
- [Jump-Start Reinforcement Learning](https://mlsanity.com/paper/2204.02372/) (2022)
- [MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research](https://mlsanity.com/paper/2109.13202/) (2021)
- [Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning](https://mlsanity.com/paper/2201.13425/) (2022)
- [Curiosity-driven Red-teaming for Large Language Models](https://mlsanity.com/paper/2402.19464/) (2024)
- [BYOL-Explore: Exploration by Bootstrapped Prediction](https://mlsanity.com/paper/2206.08332/) (2022)
- [Asymmetric self-play for automatic goal discovery in robotic manipulation](https://mlsanity.com/paper/2101.04882/) (2021)
- [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023)
- [Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation](https://mlsanity.com/paper/2110.01219/) (2021)
- [MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/2212.05698/) (2022)
- [Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain](https://mlsanity.com/paper/2109.06668/) (2021)
- [Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search](https://mlsanity.com/paper/2502.02508/) (2025)
- [Exploration via Elliptical Episodic Bonuses](https://mlsanity.com/paper/2210.05805/) (2022)
- [Self-Questioning Language Models](https://mlsanity.com/paper/2508.03682/) (2025)
- [Learning to Generate Better Than Your LLM](https://mlsanity.com/paper/2306.11816/) (2023)
- [Adversarially Guided Actor-Critic](https://mlsanity.com/paper/2102.04376/) (2021)
- [Towards A Unified Agent with Foundation Models](https://mlsanity.com/paper/2307.09668/) (2023)
- [First Return, Entropy-Eliciting Explore](https://mlsanity.com/paper/2507.07017/) (2025)
- [POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration](https://mlsanity.com/paper/2601.18779/) (2026)
- [LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities](https://mlsanity.com/paper/2504.16078/) (2025)
- [MADE: Exploration via Maximizing Deviation from Explored Regions](https://mlsanity.com/paper/2106.10268/) (2021)
- [On Bonus-Based Exploration Methods in the Arcade Learning Environment](https://mlsanity.com/paper/2109.11052/) (2021)

## Abstract (arXiv)

A grand challenge in reinforcement learning is intelligent exploration, especially when rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard-exploration domains: Montezuma's Revenge and Pitfall. On both games, current RL algorithms perform poorly, even those with intrinsic motivation, which is the dominant method to improve performance on hard-exploration domains. To address this shortfall, we introduce a new algorithm called Go-Explore. It exploits the following principles: (1) remember previously visited states, (2) first return to a promising state (without exploration), then explore from it, and (3) solve simulated environments through any available means (including by introducing determinism), then robustify via imitation learning. The combined effect of these principles is a dramatic performance improvement on hard-exploration problems. On Montezuma's Revenge, Go-Explore scores a mean of over 43k points, almost 4 times the previous state of the art. Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma's Revenge. Its max performance of nearly 18 million surpasses the human world record, meeting even the strictest definition of "superhuman" performance. On Pitfall, Go-Explore with domain knowledge is the first algorithm to score above zero. Its mean score of almost 60k points exceeds expert human performance. Because Go-Explore produces high-performing demonstrations automatically and cheaply, it also outperforms imitation learning work where humans provide solution demonstrations. Go-Explore opens up many new research directions into improving it and weaving its insights into current RL algorithms. It may also enable progress on previously unsolvable hard-exploration problems in many domains, especially those that harness a simulator during training (e.g. robotics).