Thollen's Stars
abhishekkrthakur/approachingalmost
Approaching (Almost) Any Machine Learning Problem
sweetice/Deep-reinforcement-learning-with-pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
xuehaouwa/Awesome-Trajectory-Prediction
haarnoja/sac
Soft Actor-Critic
agrimgupta92/sgan
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
colorfulfuture/Awesome-Trajectory-Motion-Prediction-Papers
ikostrikov/jaxrl
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
abduallahmohamed/Social-STGCNN
Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
lucidrains/local-attention
An implementation of local windowed attention for language modeling
NVlabs/trajdata
A unified interface to many trajectory forecasting datasets.
Jingliang-Duan/DSAC-T
DSAC-v2; DASC; Distributional Soft Actor-Critic
huang-xx/STGAT
STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction
Intelligent-Driving-Laboratory/GOPS
General Optimal control Problem Solver (GOPS), an easy-to-use PyTorch reinforcement learning solver package for industrial control.
watchernyu/REDQ
Author's PyTorch implementation of Randomized Ensembled Double Q-Learning (REDQ) algorithm.
dulucas/siMLPe
A Simple Baseline for Human Motion Prediction
AntoineTheb/RNN-RL
Experiments with reinforcement learning and recurrent neural networks
vita-epfl/s-attack
[CVPR 2022] S-attack library. Official implementation of two papers "Vehicle trajectory prediction works, but not everywhere" and "Are socially-aware trajectory prediction models really socially-aware?".
kuhess/pso-ann
Particle Swarm Optimization (PSO) to optimize Artificial Neural Network (ANN)
oist-cnru/Variational-Recurrent-Models
Codes for the study "Variational Recurrent Models for Solving Partially Observable Control Tasks", published as a conference paper at ICLR 2020 (https://openreview.net/forum?id=r1lL4a4tDB)
MeepMoop/tilecoding
Binary feature representations with tile coding
bundasmanu/CNNOptimization
Using Particle Swarm Optimization (PSO) to Optimize a CNN (Convulsional Neural Network) - using an simple dataset (not using an image dataset)
happywu/Self-Sup-Attention-RL
Self-Supervised Attention-Aware Reinforcement Learning
lakshayk12/ANN_optimization_BTP
Project based on applying hybrid meta-heuristic algorithms for optimizing classifier of Artificial neural network
AmeyDeshpande97/Motion-planning-for-an-Autonomous-Vehicles-under-Dynamic-Obstacle-Uncertainty
This project is regarding Motion Planning for Autonomous Vehicle under uncertainty. There are various kinds of uncertainty for an autonomous vehicle/autonomous robot like: Uncertainty in system configuration, Uncertainty in the system model, Uncertainty in environmental situations, Uncertainty in Future environment state.(Dynamic obstacle). So, as to deal with these uncertainties, motion planner should plan by incorporating these uncertainties. We majorly focus on dynamic obstacle uncertainty. After doing literature survey, we found that sampling-based approach scale well with respect to deal with uncertainty. So, we studied and explored following RRT variants which are use to deal with uncertainty: RRBT(Rapidly exploring Belief trees) Chance Constrained RRT(CC-RRT) RRT-FNDynamic() RRT-X We have successfully implemented RRT for Ackerman based vehicle for static obstacle.(You can see the implementation in the below video) We finally implemented RRT* as global planner and Dynamic Window approach algorithm as local planner. RRT* returned us a optimal path, we fed the path to our local planner. We simulated our dynamic moving obstacle in Pygame by incorporating random uncertain moving obstacles. Our local planner is successfully able to avoid uncertain moving dynamic obstacles and it reached it's goal destination without colliding to any of the obstacles. You can see the demo of our implementation in the below video which is at the right hand side and project presentation video at the left hand side.
dhana-jaya-kumar/DeepRL_Path_Planner
A framework for path-planing and obstacle avoidance using Deep Reinforcement Learning Techniques.
yannickBurkhardt/ReinforcementPlanner
Dynamic Path Planning using Reinforcement Learning (Project from Advanced Deep Learning for Robotics course at Technical University of Munich, SS22)
AmeyDeshpande97/Motion-Prediction-of-Agents-in-the-Vicinity-of-Self-Driving-Car
The goal of the project was to predict the motion of an autonomous vehicle and the surrounding agents given their trajectory for the past one second. For this, we used rasterized images as an input to a CNN baseline. To the given parameters, we added the velocities along x and y direction. This helped predicting instantaneous velocity of the agent at every time step. In addition, the baseline was modified by adding an LSTM decoder to study their impact on predictions. Instantaneous velocity was an added parameter for the model and predicting instantaneous velocities can be used to improve the motion prediction of the agents and can facilitate agent interaction and cooperative driving
CHUENGMINCHOU/AW-PER-A2C
The test code for the paper "Attention-based advantage actor-critic algorithm with prioritized experience replay for complex 2-D robotic motion planning".
ShaniGam/pytorch-a3c-attention
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) with Soft Attention
TheLeprechaun25/neural-improvement-heuristics
Official Pytorch implementation of the paper "Neural Improvement Heuristics for Graph Combinatorial Optimization Problems"