EvoTorch: Scalable Evolutionary Computation in Python

1 code implementation • 24 Feb 2023 • Nihat Engin Toklu, Timothy Atkinson, Vojtěch Micka, Paweł Liskowski, Rupesh Kumar Srivastava

Evolutionary computation is an important component within various fields such as artificial intelligence research, reinforcement learning, robotics, industrial automation and/or optimization, engineering design, etc.

reinforcement-learning Reinforcement Learning (RL)

ClipUp: A Simple and Powerful Optimizer for Distribution-based Policy Evolution

1 code implementation • 5 Aug 2020 • Nihat Engin Toklu, Paweł Liskowski, Rupesh Kumar Srivastava

In these algorithms, gradients of the total reward with respect to the policy parameters are estimated using a population of solutions drawn from a search distribution, and then used for policy optimization with stochastic gradient ascent.

Continuous Control Humanoid Control

Learning to Play Othello with Deep Neural Networks

1 code implementation • 17 Nov 2017 • Paweł Liskowski, Wojciech Jaśkowski, Krzysztof Krawiec

Achieving superhuman playing level by AlphaGo corroborated the capabilities of convolutional neural architectures (CNNs) for capturing complex spatial patterns.