mlsanityData to 14 Oct 2026

Natural Environment Benchmarks for Reinforcement Learning

arXiv 1811.06032 ↗First posted 14 Nov 2018cs.LG cs.AI stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

While current benchmark reinforcement learning (RL) tasks have been useful to drive progress in the field, they are in many ways poor substitutes for learning with real-world data. By testing increasingly complex RL algorithms on low-complexity simulation environments, we often end up with brittle RL policies that generalize poorly beyond the very specific domain. To combat this, we propose three new families of benchmark RL domains that contain some of the complexity of the natural world, while still supporting fast and extensive data acquisition. The proposed domains also permit a characterization of generalization through fair train/test separation, and easy comparison and replication of results. Through this work, we challenge the RL research community to develop more robust algorithms that meet high standards of evaluation.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 7; 2023: 5; 2024: 6; 2025: 2; 2026: 2.

32 papers.

Sort:

By area:

  1. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  2. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  3. 2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 109
  4. 2021The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixelscited by 100
  5. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 99
  6. 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
  7. 2022Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learningcited by 34
  8. 2021DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneckcited by 31
  9. 2021Procedural Generalization by Planning with Self-Supervised World Modelscited by 31
  10. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 25
  11. 2021Learning Representations for Pixel-based Control: What Matters and Why?cited by 24
  12. 2023HarmonyDream: Task Harmonization Inside World Modelscited by 22
20 more
  1. 2024Learning Latent Dynamic Robust Representations for World Modelscited by 21
  2. 2026stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluationcited by 20
  3. 2021Domain Adversarial Reinforcement Learningcited by 19
  4. 2023RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictabilitycited by 18
  5. 2024IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoningcited by 16
  6. 2023Invariant Causal Imitation Learning for Generalizable Policiescited by 15
  7. 2022Learning to Generalize with Object-centric Agents in the Open World Survival Game Craftercited by 13
  8. 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learningcited by 13
  9. 2023Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectoriescited by 9
  10. 2024iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learningcited by 9
  11. 2022Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hexcited by 8
  12. 2021Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environmentscited by 6
  13. 2024Bisimulation metric for Model Predictive Controlcited by 6
  14. 2022Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similaritiescited by 4
  15. 2024R3L: Relative Representations for Reinforcement Learningcited by 2
  16. 2022Generalization Through the Lens of Learning Dynamicscited by 0
  17. 2023Towards Control-Centric Representations in Reinforcement Learning from Imagescited by 0
  18. 2024Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codescited by 0
  19. 2025MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learningcited by 0
  20. 2026LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPCcited by 0