Pixelatory / PSO-GPU
A particle swarm optimizer using the GPU (PyTorch).
☆15Updated 2 years ago
Alternatives and similar repositories for PSO-GPU:
Users that are interested in PSO-GPU are comparing it to the libraries listed below
- Swarm learning algorithm☆11Updated 3 years ago
- The Flexible Job Shop Problem (FJSP) is an extension of the classical job shop scheduling problem which allows an operation to be process…☆19Updated 9 years ago
- Multi-Objective Reinforcement Learning sandbox☆10Updated 3 years ago
- Particle Swarm Optimizer For Neural Network Training☆56Updated 6 years ago
- Pointer Networks Implementation to solve Convex-Hull and TSP problems using supervised and RL training.☆11Updated last year
- CVaR-based Flight Energy Risk Assessment for Multirotor UAVs using a Deep Energy Model☆24Updated last year
- ☆10Updated 4 years ago
- Exploring whether DRQN + action prior + state-based expert + history-based entropy-reduction expert☆8Updated 3 years ago
- A simple, bare bones, implementation of differential evolution optimization.☆49Updated 5 years ago
- Source code for Pathfinding in Stochastic Environments paper.☆15Updated 2 years ago
- RL-Toolkit: A Research Framework for Robotics☆19Updated 2 months ago
- Fully Cooperative Multi-Agent Deep Reinforcement Learning☆25Updated 5 years ago
- GYM based Reinforcement learning library that connects Ant colony optimization and Sarsa Lambda.☆9Updated 5 years ago
- Project exploring Multi Task Deep Reinforcement Learning neural network architectures and algorithms with Open AI Gym and TensorFlow☆17Updated 6 years ago
- Pytorch implementation of Randomized Ensembled Double Q-learning (REDQ)☆21Updated 4 years ago
- Model-based reinforcement learning using CEM, MPC and PETS☆16Updated 5 years ago
- Graph convolutional memory for reinforcement learning☆23Updated 3 years ago
- ☆9Updated 4 years ago
- Official implementation of "Graph Meta-Reinforcement Learning for TransferableAutonomous Mobility-on-Demand"☆14Updated 3 years ago
- Tuning the PI controller parameters by using a contextual bandit approach☆11Updated 3 years ago
- Deep Reinforcement Learning by using an on-policy adaptation of Maximum a Posteriori Policy Optimization (MPO)☆17Updated 3 years ago
- Evolutionary Computation: A Modern Perspective |<...>| This is an online book, which is free-access and actively-updated (1st Edition: fr…☆51Updated 3 weeks ago
- JAX-based implementation for multi-agent path planning (MAPP) in continuous spaces.☆47Updated 2 years ago
- This repository provides a brief introduction to PID control by using Python examples in Jupyter notebooks.☆18Updated last year
- New reinforcement algorithm base on DDPG☆18Updated 5 years ago
- ☆19Updated 6 years ago
- pfevaluator: A library for evaluating performance metrics of Pareto fronts in multiple/many objective optimization problems☆34Updated last year
- Part of a research scholarship. I built a basic 2d driving sim with simulated lidar data to train Deep Q Neural Network. So far after abo…☆11Updated 8 years ago
- Multi-objective reinforcement learning deals with finding policies for tasks where there are multiple distinct criteria to optimize for. …☆21Updated 6 years ago
- A peper list for machine learning models solving combinatorial problems, NP-hard problems and problems in graphs.☆14Updated 4 years ago