mlsanityData to 14 Oct 2026

Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision

arXiv 2206.11733 ↗First posted 23 Jun 2022cs.LG cs.AI cs.ROcited by 3

Not on the map. Why?

Abstract (arXiv)

Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful in many applications. We propose a novel method for training such a goal-conditioned agent without any external rewards or any domain knowledge. We use random walk to train a reachability network that predicts the similarity between two states. This reachability network is then used in building goal memory containing past observations that are diverse and well-balanced. Finally, we train a goal-conditioned policy network with goals sampled from the goal memory and reward it by the reachability network and the goal memory. All the components are kept updated throughout training as the agent discovers and learns new goals. We apply our method to a continuous control navigation and robotic manipulation tasks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 17 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

14 of 17 references.

References · 14

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Hindsight Experience Replaycited by 1,136
  3. 2018Visual Reinforcement Learning with Imagined Goalscited by 251
  4. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 174
  5. 2019Planning with Goal-Conditioned Policiescited by 149
  6. 2017Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Playcited by 141
  7. 2021Discovering and Achieving Goals via World Modelscited by 131
  8. 2018Episodic Curiosity through Reachabilitycited by 109
  9. 2018Unsupervised Control Through Non-Parametric Discriminative Rewardscited by 102
  10. 2020Learning with AMIGo: Adversarially Motivated Intrinsic Goalscited by 88
  11. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 72
  12. 2019Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discoverycited by 68
2 more
  1. 2018Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learningcited by 24
  2. 2019Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learningcited by 18

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2023Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shapingcited by 25
  2. 2023Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Reviewcited by 3
  3. 2022Task-Agnostic Learning to Accomplish New Taskscited by 0