• Corpus ID: 231861802

Learning Equational Theorem Proving

  title={Learning Equational Theorem Proving},
  author={Jelle Piepenbrock and Tom M. Heskes and Mikol'avs Janota and Josef Urban},
We develop Stratified Shortest Solution Imitation Learning (3SIL) to learn equational theorem proving in a deep reinforcement learning (RL) setting. The self-trained models achieve state-of-the-art performance in proving problems generated by one of the top open conjectures in quasigroup theory, the Abelian Inner Mapping (AIM) Conjecture. To develop the methods, we first use two simpler arithmetic rewriting tasks that share tree-structured proof states and sparse rewards with the AIM problems… 

Figures and Tables from this paper

Similarity-Based Equational Inference in Physics

A symbolic similarity-based heuristic search is implemented to solve the equation reconstruction task as an early step towards multi-hop equational inference in physics.

PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics

A collection of datasets developed to evaluate the performance of language models in this regard are presented, which measure capabilities with respect to sentence ordering, position, section prediction, and discourse coherence.



Deep Reinforcement Learning for Synthesizing Functions in Higher-Order Logic

A deep reinforcement learning framework based on self-supervised learning within the proof assistant HOL4 with a success rate of 65% on combinator synthesis problems outperforming state-of-the-art ATPs run with their best general set of strategies.

Reinforcement Learning of Theorem Proving

A theorem proving algorithm that uses practically no domain heuristics for guiding its connection-style proof search and solves within the same number of inferences over 40% more problems than a baseline prover, which is an unusually high improvement in this hard AI domain.

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

This paper proposes a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting and demonstrates that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.

Dota 2 with Large Scale Deep Reinforcement Learning

By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.

Behavioral Cloning from Observation

This work proposes a two-phase, autonomous imitation learning technique called behavioral cloning from observation (BCO), that allows the agent to acquire experience in a self-supervised fashion to develop a model which is then utilized to learn a particular task by observing an expert perform that task without the knowledge of the specific actions taken.

Self-Imitation Learning

This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions to verify the hypothesis that exploiting past good experiences can indirectly drive deep exploration.

Learning to Search in Branch and Bound Algorithms

This work addresses the key challenge of learning an adaptive node searching order for any class of problem solvable by branch-and-bound by applying its algorithm to linear programming based branch- and-bound for solving mixed integer programs (MIP).

Human-level control through deep reinforcement learning

This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Reinforcement Learning: An Introduction

This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.