myGym enables fast prototyping of RL in the area of robotic manipulation and navigation.You can train different robots, in several environments on various tasks. There is automatic evaluation and benchmark tool. From version 2.1 there is support for multi-step tasks, multi-reward training and multi-network architectures.

The code accompaniment for the CoRL 2020 paper: A User's Guide to Calibrating Robotics Simulators (https://arxiv.org/abs/2011.08985), from NVIDIA Research Seattle.

Implementation of the paper "A Deep Reinforcement Learning-based Adaptive Charging Policy for WRSNs"

Print NGSPICE result as JSON

Fleet2D: A lightweight, 2D simulator for fast, long-term, consumer robotics applications.

Source code to accompany the article series Building Machines in Code - Creating Digital Systems Emulators and Simulators on http://www.coderancher.us

Energy-based neuronal models (eLIF and mAdExp)

SMARTER is an advanced simulator for robots navigating tile grids, utilizing the Mesa framework to model interactions, blocked areas, and customizable movement and cutting behaviors.

A game of probability & optimization simulating Optimal Stopping Problem variants. Supports multiple agents with different policies.

Correlating branch prediction simulator

A simulator of Shanghai Yaohua electronic scale, which can communicate with the host computer in continuous mode and command mode, and can specify gross weight and tare weight.

Excellent Environments for Reinforcement Learning Benchmarking