115 skills found · Page 4 of 4
s1ddh-rth / HumanoidClimb RLThis project explores the application of reinforcement learning (RL) to train humanoid robots for dynamic rock climbing movements, focusing on achieving the challenging "dyno" maneuver. Using the Proximal Policy Optimization (PPO) algorithm, the simulation integrates physics-based environments to model realistic climbing scenarios.
cherylwang20 / GCRL UR10eGCRL_UR10e is a sim-to-real reinforcement learning framework for the UR10e robotic arm, using goal-conditioned policies trained in simulation and deployed with either servoJ or moveJ control. The system leverages visual goals and supports real-time testing for reach-and-grasp tasks.
ianyepan / Fluid Simulation OFAn openFrameworks port of Coding Train's Fluid Simulation in Processing
FedericoRollo / LQR Controller For A Magnetic Levitation TrainModeling, simulation and control of a maglev train in a Matlab & Simulonk ambient. The LQR technique has been used to control the behavior of the train in a linear and curvilinear trajectory.
cormacmadden / Cloth Simulation Database GeneratorBlender and Houdini Scripts for generating Physics-Based Cloth Simulations intended to train Machine Learning Algorithms
alecfilios / Training Intelligent Game Agents Through Competitive Reinforcement LearningThis diploma thesis deals with the implementation of a simulation in three dimensions, in which there exist some agents. These agents are trained to perform specific tasks. Using the Unity3d platform in conjunction with the ml-agents library provided, we construct a simulation environment suitable to carry through the needs of our training requirements. The technique of artificial intelligence used is reinforcement learning, one of the branches of the broader concept called machine learning.
FastOpticalSpectrum / FOSFOS, which means "light" in Greek, is an open-source program used for Fast Optical Spectrum (FOS) calculations of nanoparticle media by combining Mie theory with either Monte Carlo simulations or a pre-trained deep neural network.
thiennhanng191 / FireTraining Simulation VRA 3D simulation in VR for fire training
peterbhase / Counterfactual Simulation TrainingCodebase for paper: "Counterfactual Simulation Training for Chain-of-Thought Faithfulness"
sandeepthalapanane / Safe Intersection Navigation AVs Using Reinforcement LearningLeveraged Deep Q-Learning to train an autonomous vehicle agent to safely navigate intersections in a SUMO simulation, achieving efficient traffic flow through reinforcement learning.
russelljjarvis / SpikingNeuralNetworks .jlJulia has enough tools to support fitting spiking neural network models to data. Pythons slow speed necessitates calls to external simulators (two language problem) to do network simulation. As much as possible it would be nice to do fast, efficient data fitting of spike trains to network models in one language, lets try to do that here.
ncbdrck / Sb3 Ros SupportThis package provides ROS support for Stable Baselines3. It allows you to train robotics RL agents in the real world and simulations using ROS and SB3.
ChandhanSaai / Reinforcement Learning Based Pick And Place Task For Panda RobotThis project leverages robosuite, a simulation framework for robotic manipulation, in combination with Stable Baselines3 (SB3) to train and evaluate a Soft Actor-Critic (SAC) agent for the Pick-and-Place task.
andomeder / Act Mujoco ManipulationEnd-to-end implementation of Action Chunking Transformers (ACT) for imitation learning in robot manipulation tasks. Trained and evaluated in MuJoCo simulation on a pick-and-place task using the ROBOTIS FFW humanoid robot.
SpectoLabs / Api Simulation TrainingReality is Overrated: API Simulation for Microservice Testing - Training Workshop
vitelot / TrainingMacroscopic simulation of trains in a railway system
japlete / Train Ops SimOptimization of a train scheduling simulation using Reinforcement Learning
aminfakhereldine / TrainSecThis project presents the code for TrainSec, a simulation framework that facilitates security modeling and evaluation in networks of communication-based train control (CBTC) systems.
sk-surya / Solver Train SchedulerA Simulation based Optimization Solver to Schedule Train Departures and Minimize Passenger Waiting Times
Vaishnav2299 / Kinematic Modelling Of SAM Target Trajectory SimulationSimulation Of Surface-To-Air Missile -- Target Intercept Trajectory Simulation using Matlab. this project was completed during the Internship at Aeronautical Development Establishment , Defence Research & Development Organization, Ministry Of Defence India. This code was integrated with the Indian Light Combat Aircraft jet fighter simulator used to train the pilots.
