mlsanityData to 7 Oct 2026

The Sandbox Environment for Generalizable Agent Research (SEGAR)

arXiv 2203.10351 ↗First posted 19 Mar 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress. While there has been notable headway, current benchmarks either do not provide suitable exposure nor intuitive control of the underlying factors, are not easy-to-implement, customizable, or extensible, or are computationally expensive to run. We built the Sandbox Environment for Generalizable Agent Research (SEGAR) with all of these things in mind. SEGAR improves the ease and accountability of generalization research in RL, as generalization objectives can be easy designed by specifying task distributions, which in turns allows the researcher to measure the nature of the generalization objective. We present an overview of SEGAR and how it contributes to these goals, as well as experiments that demonstrate a few types of research questions SEGAR can help answer.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 81 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

52 of 81 references.

References · 52

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2016OpenAI Gymcited by 1,684
  5. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  6. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  7. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  8. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  9. 2020Mastering Atari with Discrete World Modelscited by 990
  10. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  11. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  12. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
38 more
  1. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  2. 2018MINE: Mutual Information Neural Estimationcited by 680
  3. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  4. 2019On Variational Bounds of Mutual Informationcited by 550
  5. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  6. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  7. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  8. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  9. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  10. 2020Data-Efficient Reinforcement Learning with Self-Predictive Representationscited by 309
  11. 2018TextWorld: A Learning Environment for Text-based Gamescited by 304
  12. 2019Challenges of Real-World Reinforcement Learningcited by 282
  13. 2018Learning to Drive in a Daycited by 266
  14. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  15. 2020The NetHack Learning Environmentcited by 196
  16. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 193
  17. 2021Reinforcement Learning with Prototypical Representationscited by 179
  18. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  19. 2019Unsupervised State Representation Learning in Ataricited by 144
  20. 2018Assessing Generalization in Deep Reinforcement Learningcited by 132
  21. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 128
  22. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  23. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  24. 2020The Ingredients of Real-World Robotic Reinforcement Learningcited by 111
  25. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  26. 2021Pretraining Representations for Data-Efficient Reinforcement Learningcited by 105
  27. 2021Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observabilitycited by 102
  28. 2019Observational Overfitting in Reinforcement Learningcited by 90
  29. 2020Deep Reinforcement and InfoMax Learningcited by 79
  30. 2017Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigationcited by 74
  31. 2021On The Effect of Auxiliary Tasks on Representation Dynamicscited by 56
  32. 2019Obstacle Tower: A Generalization Challenge in Vision, Control, and Planningcited by 54
  33. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  34. 2020PDDLGym: Gym Environments from PDDL Problemscited by 45
  35. 2021SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policiescited by 42
  36. 2019Locality and compositionality in zero-shot learningcited by 29
  37. 2018Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learningcited by 24
  38. 2021Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLcited by 20

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.