mlsanityData to 7 Oct 2026

Improving generalization to new environments and removing catastrophic forgetting in Reinforcement Learning by using an eco-system of agents

arXiv 2204.06550 ↗First posted 13 Apr 2022cs.AI cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Adapting a Reinforcement Learning (RL) agent to an unseen environment is a difficult task due to typical over-fitting on the training environment. RL agents are often capable of solving environments very close to the trained environment, but when environments become substantially different, their performance quickly drops. When agents are retrained on new environments, a second issue arises: there is a risk of catastrophic forgetting, where the performance on previously seen environments is seriously hampered. This paper proposes a novel approach that exploits an eco-system of agents to address both concerns. Hereby, the (limited) adaptive power of individual agents is harvested to build a highly adaptive eco-system.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 13 Apr 2022.

Builds on

17 of 23 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  4. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  5. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  6. 2018An Introduction to Deep Reinforcement Learningcited by 201
  7. 2018Assessing Generalization in Deep Reinforcement Learningcited by 132
  8. 2018Generalization and Regularization in DQNcited by 117
  9. 2019Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneckcited by 101
  10. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 80
  11. 2018Gotta Learn Fast: A New Benchmark for Generalization in RLcited by 59
  12. 2018Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgettingcited by 46
5 more
  1. 2020Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learningcited by 37
  2. 2020Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learningcited by 26
  3. 2020Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networkscited by 17
  4. 2020Reinforcement Learning Generalization with Surprise Minimizationcited by 10
  5. 2020A Brief Look at Generalization in Visual Meta-Reinforcement Learningcited by 5

Built on by

Not cited yet.