mlsanityData to 14 Oct 2026

Why Goal-Conditioned Reinforcement Learning Works: Relation to Dual Control

arXiv 2512.06471 ↗First posted 6 Dec 2025cs.LG cs.AIcited by 0

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

Abstract (arXiv)

Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on optimal control. In particular, we derive an optimality gap between more classical, often quadratic, objectives and the goal-conditioned reward, elucidating the success of goal-conditioned RL and why classical ``dense'' rewards can falter. We then consider the partially observed Markov decision setting and connect state estimation to our probabilistic reward, making the goal-conditioned reward well suited to dual control problems. The advantages of goal-conditioned policies are validated on nonlinear and uncertain environments using both RL and predictive control techniques.

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 9 of its 24 references that are in the map. First posted on arXiv 6 Dec 2025.

Builds on

9 of 24 references.

References · 9

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 482
  3. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 253
  4. 2024SOAP: Improving and Stabilizing Shampoo using Adamcited by 192
  5. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  6. 2020C-Learning: Learning to Achieve Goals via Recursive Classificationcited by 103
  7. 2020Deep Learning Alternative to Explicit Model Predictive Control for Unknown Nonlinear Systemscited by 22
  8. 2022Optimality Guarantees for Particle Belief Approximation of POMDPscited by 20
  9. 2025A view on learning robust goal-conditioned value functions: Interplay between RL and MPCcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reward-Conditioned Reinforcement Learning
  2. 2025A tale of two goals: leveraging sequentiality in multi-goal scenarios
  3. 2026Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
  4. 2022Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
  5. 2025Dual Goal Representations
  6. 2025Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks
  7. 2026Abstraction for Offline Goal-Conditioned Reinforcement Learning
  8. 2026Relating Reinforcement Learning to Dynamic Programming-Based Planning