mlsanityData to 7 Oct 2026

Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation

arXiv 2209.12347 ↗First posted 25 Sep 2022eess.SY cs.AI cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a series of 2D navigation tasks. We show how our methods can leverage animal videos to improve performance over RL algorithms that do not leverage such observations.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 25 Sep 2022.

Builds on

23 of 34 references.

References · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  4. 2015Trust Region Policy Optimizationcited by 2,503
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  9. 2017Constrained Policy Optimizationcited by 928
  10. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  11. 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 750
  12. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 647
11 more
  1. 2018Behavioral Cloning from Observationcited by 482
  2. 2018Maximum a Posteriori Policy Optimisationcited by 318
  3. 2019Challenges of Real-World Reinforcement Learningcited by 282
  4. 2016Safe and Efficient Off-Policy Reinforcement Learningcited by 260
  5. 2021Offline Reinforcement Learning with Fisher Divergence Critic Regularizationcited by 237
  6. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
  7. 2020Reinforcement Learning with Videos: Combining Offline Observations with Interactioncited by 80
  8. 2021Universal Off-Policy Evaluationcited by 43
  9. 2021Generalized Proximal Policy Optimization with Sample Reusecited by 39
  10. 2021Domain Adaptation In Reinforcement Learning Via Latent Unified State Representationcited by 33
  11. 2021Revisiting Peng's Q(λ) for Modern Reinforcement Learningcited by 19

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2023Adversarial Imitation Learning from Visual Observations using Latent Informationcited by 10
  2. 2024Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learningcited by 9
  3. 2025Beyond Domain Randomization: Event-Inspired Perception for Visually Robust Adversarial Imitation from Videoscited by 1
  4. 2024A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observationscited by 0