gym-saturation: an OpenAI Gym environment for saturation provers
نویسندگان
چکیده
`gym-saturation` is an OpenAI Gym environment for reinforcement learning (RL) agents capable of proving theorems. Currently, only theorems written in a formal language the Thousands Problems Theorem Provers (TPTP) library clausal normal form (CNF) are supported. implements 'given clause' algorithm (similar to one used Vampire and E Prover). Being Python, was inspired by PyRes. In contrast monolithic architecture typical Automated Prover (ATP), gives different opportunities select clauses themselves train from their experience. Combined with particular agent, can work as ATP. Even non trained agent based on heuristics, find refutations 688 (of 8257) CNF problems TPTP v7.5.0.
منابع مشابه
OpenAI Gym
OpenAI Gym1 is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their results and compare the performance of algorithms. This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.
متن کاملMDP environments for the OpenAI Gym
The OpenAI Gym provides researchers and enthusiasts with simple to use environments for reinforcement learning. Even the simplest environment have a level of complexity that can obfuscate the inner workings of RL approaches and make debugging difficult. This whitepaper describes a Python framework1 that makes it very easy to create simple Markov-Decision-Process environments programmatically by...
متن کاملExtending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo
This paper presents an extension of the OpenAI Gym for robotics using the Robot Operating System (ROS) and the Gazebo simulator. The content discusses the software architecture proposed and the results obtained by using two Reinforcement Learning techniques: Q-Learning and Sarsa. Ultimately, the output of this work presents a benchmarking system for robotics that allows different techniques and...
متن کاملClosing the loop between neural network simulators and the OpenAI Gym
Since the enormous breakthroughs in machine learning over the last decade, functional neural network models are of growing interest for many researchers in the field of computational neuroscience. One major branch of research is concerned with biologically plausible implementations of reinforcement learning, with a variety of different models developed over the recent years. However, most studi...
متن کاملGym Membership: an Application of theWeibull Distribution
The Swedish physicist, Waloddi Weibull, is renowned for formulating a family of probability distributions for modelling the variability of nonnegative, quantitative, random phenomena (see reference 3). The distribution was originally designed to model the breaking strength of steel (Weibull was scientific advisor to Bofors, the Swedish steel company) but, since then, Weibull analysis has evolve...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of open source software
سال: 2022
ISSN: ['2475-9066']
DOI: https://doi.org/10.21105/joss.03849