mlsanityData to 14 Oct 2026

Visual Goal-Directed Meta-Learning with Contextual Planning Networks

arXiv 2111.09908 ↗First posted 18 Nov 2021cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The goal of meta-learning is to generalize to new tasks and goals as quickly as possible. Ideally, we would like approaches that generalize to new goals and tasks on the first attempt. Toward that end, we introduce contextual planning networks (CPN). Tasks are represented as goal images and used to condition the approach. We evaluate CPN along with several other approaches adapted for zero-shot goal-directed meta-learning. We evaluate these approaches across 24 distinct manipulation tasks using Metaworld benchmark tasks. We found that CPN outperformed several approaches and baselines on one task and was competitive with existing approaches on others. We demonstrate the approach on a physical platform on Jenga tasks using a Kinova Jaco robotic arm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 33 references that are in the map. First posted on arXiv 18 Nov 2021.

Builds on

22 of 33 references.

References · 22

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  4. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  5. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  6. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  7. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  8. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  9. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 274
  10. 2015Deep Spatial Autoencoders for Visuomotor Learningcited by 153
  11. 2017Value Prediction Networkcited by 117
  12. 2018Zero-Shot Visual Imitationcited by 117
10 more
  1. 2016The Predictron: End-To-End Learning and Planningcited by 93
  2. 2017Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulationcited by 90
  3. 2020Learning to Continually Learncited by 84
  4. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 76
  5. 2016Unsupervised Perceptual Rewards for Imitation Learningcited by 65
  6. 2018TACO: Learning Task Decomposition via Temporal Alignment for Controlcited by 62
  7. 2018Universal Planning Networkscited by 30
  8. 2019Watch, Try, Learn: Meta-Learning from Demonstrations and Rewardcited by 28
  9. 2020Hallucinative Topological Memory for Zero-Shot Visual Planningcited by 25
  10. 2017Model-Based Planning with Discrete and Continuous Actionscited by 7

Built on by

Not cited yet.