mohammadasadolahi's Projects
reinforcement learning Double Deep Q Learning (DDQN) method to solve OpenAi Gym "LunarLander-v2" by usnig Double Deep NeuralNetworks
reinforcement learning DQN method to solve OpenAi Gym "LunarLander-v2" by usnig a Deep Neuralnetwork
reinforcement learning Dueling Deep Q Learning (DuelingDQN) method to solve OpenAi Gym "LunarLander-v2" by usnig Dueling Deep NeuralNetworks
A simpl but proper framework to accurately evaluate RL algorithms and fair comparison between different RL algorithms
Gradient Free Reinforcement Learning solving Openai gym LunarLanderV2 by Evolution Strategy (Genetic Algorithm)
image retrival on coral dataset using Euclidean distance in python
infinite smart vector with automatic memory management template in c++
implementation of KL-UCB official paper
solving knapsack problem with n items with GA(genetic algorithm)
Multilayer Perceptron Neural network for binary classification between two type of breast cancer ("benign" and "malignant" )using Wisconsin Breast Cancer Database
find arrangement for n Queens in n*n board of chees using Genetic algorithms
Combining experience replay buffer whith Actor-Critic algorithm to expedite learning procedure by offline learning
Deep Q learning algorithm for cryptocurrency trade deployed with Tensorflow (keras) in python
solving a simple 4*4 Gridworld almost similar to openAI gym FrozenLake using Temporal difference method Reinforcement Learning
solving a simple 4*4 Gridworld almost similar to openAI gym frozenlake using Monte-Carlo method Reinforcement Learning
solving a simple 4*4 Gridworld almost similar to openAI gym frozenlake using value iteration method Reinforcement Learning
solving a simple 4*4 Gridworld almost similar to openAI gym FrozenLake using Qlearning Temporal difference method Reinforcement Learning
solving a simple 4*4 Gridworld almost similar to openAI gym FrozenLake using SARSA Temporal difference method Reinforcement Learning
Reinforcement Learning solving a simple 4*4_ Gridworld using MonteCarlo method by using linear approximator
Reinforcement Learning solving a simple 4*4_ Gridworld using Q-learning by linear approximator
smart pointer template class using Boost library ptr in c++
solving tsp with aco whith full graphic view in python
solving TSP (traveling sales man) using genetic algorithm in python
Stochastic Off-Policy Actor-Critic Algorithm
Dynamic NN for regression written in Tensorflow 2.0
Simple linear regressor that tries to approximate a simple function deployed in Tensorflow 2.0 without Keras
Thompson Sampling for K-actions stochastic bandit with normal reward distribution
solving tsp problem with genetic algorithm in c++