mlsanityData to 7 Oct 2026

Curiosity-driven RL for symbolic equation solving

arXiv 2510.17022 ↗First posted 19 Oct 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We explore if RL can be useful for symbolic mathematics. Previous work showed contrastive learning can solve linear equations in one variable. We show model-free PPO citeschulman2017proximal augmented with curiosity-based exploration and graph-based actions can solve nonlinear equations such as those involving radicals, exponentials, and trig functions. Our work suggests curiosity-based exploration may be useful for general symbolic reasoning tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 15 references that are in the map. First posted on arXiv 19 Oct 2025.

Builds on

9 of 15 references.

References · 9

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  3. 2018Exploration by Random Network Distillationcited by 966
  4. 2019Self-Supervised Exploration via Disagreementcited by 263
  5. 2020Never Give Up: Learning Directed Exploration Strategiescited by 210
  6. 2020RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environmentscited by 135
  7. 2021Contrastive Reinforcement Learning of Symbolic Reasoning Domainscited by 17
  8. 2024Symbolic Equation Solving via Reinforcement Learningcited by 4
  9. 2023RLLTE: Long-Term Evolution Project of Reinforcement Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search
  2. 2026Adaptive Problem Generation via Symbolic Representations
  3. 2026VERIFY-RL: Verifiable Recursive Decomposition for Reinforcement Learning in Mathematical Reasoning
  4. 2022Peano: Learning Formal Mathematical Reasoning
  5. 2025Mathematical exploration and discovery at scale
  6. 2024AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs
  7. 2025Interactive Symbolic Regression through Offline Reinforcement Learning: A Co-Design Framework
  8. 2024Interactive Symbolic Regression through Offline Reinforcement Learning: A Co-Design Framework