mlsanityData to 14 Oct 2026

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning

arXiv 2404.12999 ↗First posted 19 Apr 2024cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Exploration efficiency poses a significant challenge in goal-conditioned reinforcement learning (GCRL) tasks, particularly those with long horizons and sparse rewards. A primary limitation to exploration efficiency is the agent's inability to leverage environmental structural patterns. In this study, we introduce a novel framework, GEASD, designed to capture these patterns through an adaptive skill distribution during the learning process. This distribution optimizes the local entropy of achieved goals within a contextual horizon, enhancing goal-spreading behaviors and facilitating deep exploration in states containing familiar structural patterns. Our experiments reveal marked improvements in exploration efficiency using the adaptive skill distribution compared to a uniform skill distribution. Additionally, the learned skill distribution demonstrates robust generalization capabilities, achieving substantial exploration progress in unseen tasks containing similar local structures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 36 of its 40 references that are in the map. First posted on arXiv 19 Apr 2024.

Builds on

36 of 40 references.

References · 36

  1. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  2. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  5. 2018Exploration by Random Network Distillationcited by 993
  6. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 752
  7. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  8. 2016Deep Exploration via Bootstrapped DQNcited by 527
  9. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
  10. 2019Self-Supervised Exploration via Disagreementcited by 265
  11. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 259
  12. 2017Count-Based Exploration with Neural Density Modelscited by 257
24 more
  1. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  2. 2020Never Give Up: Learning Directed Exploration Strategiescited by 212
  3. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 174
  4. 2017Deep Exploration via Randomized Value Functionscited by 156
  5. 2015Incentivizing Exploration In Reinforcement Learning With Deep Predictive Modelscited by 154
  6. 2021Discovering and Achieving Goals via World Modelscited by 131
  7. 2017Stochastic Neural Networks for Hierarchical Reinforcement Learningcited by 124
  8. 2020Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skillscited by 122
  9. 2018Count-Based Exploration with the Successor Representationcited by 112
  10. 2018Episodic Curiosity through Reachabilitycited by 109
  11. 2018Model-Based Active Explorationcited by 105
  12. 2020Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learningcited by 102
  13. 2020Learning with AMIGo: Adversarially Motivated Intrinsic Goalscited by 88
  14. 2019Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewardscited by 78
  15. 2021Hierarchical Skills for Efficient Explorationcited by 38
  16. 2023Planning Goals for Explorationcited by 28
  17. 2018DORA The Explorer: Directed Outreaching Reinforcement Action-Selectioncited by 27
  18. 2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 26
  19. 2021Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learningcited by 23
  20. 2018Deep Curiosity Search: Intra-Life Exploration Can Improve Performance on Challenging Deep Reinforcement Learning Problemscited by 12
  21. 2020Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learningcited by 9
  22. 2022ASPiRe:Adaptive Skill Priors for Reinforcement Learningcited by 7
  23. 2023Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learningcited by 6
  24. 2022Goal Exploration Augmentation via Pre-trained Skills for Sparse-Reward Long-Horizon Goal-Conditioned Reinforcement Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
  2. 2026Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
  3. 2026Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals
  4. 2025Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL
  5. 2025HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents
  6. 2024Reinforcement Learning with a Focus on Adjusting Policies to Reach Targets
  7. 2026Search Inspired Exploration in Reinforcement Learning
  8. 2025DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning