mlsanityData to 7 Oct 2026

Improving generalization in reinforcement learning through forked agents

arXiv 2212.06451 ↗First posted 13 Dec 2022cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

An eco-system of agents each having their own policy with some, but limited, generalizability has proven to be a reliable approach to increase generalization across procedurally generated environments. In such an approach, new agents are regularly added to the eco-system when encountering a new environment that is outside of the scope of the eco-system. The speed of adaptation and general effectiveness of the eco-system approach highly depends on the initialization of new agents. In this paper we propose different initialization techniques, inspired from Deep Neural Network initialization and transfer learning, and study their impact.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 20 references that are in the map. First posted on arXiv 13 Dec 2022.

Builds on

15 of 20 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  3. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  4. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  5. 2018Assessing Generalization in Deep Reinforcement Learningcited by 132
  6. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  7. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 80
  8. 2018Gotta Learn Fast: A New Benchmark for Generalization in RLcited by 59
  9. 2017Divide-and-Conquer Reinforcement Learningcited by 46
  10. 2020Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learningcited by 37
  11. 2020Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learningcited by 26
  12. 2022Improving Policy Optimization with Generalist-Specialist Learningcited by 19
3 more
  1. 2020Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networkscited by 17
  2. 2020Reinforcement Learning Generalization with Surprise Minimizationcited by 10
  3. 2021Weight Initialization Techniques for Deep Learning Algorithms in Remote Sensing: Recent Trends and Future Perspectivescited by 8

Built on by

Not cited yet.