Pinned Repositories
Acrobot-Policy-Gradients
DDPG_Fetch
Exploring the performance of Prioritized Experience Replay (PER) with the DDPG+HER scheme on the Fetch Robotics Environemnt
Descent-Algorithms
Exploring convergence trend for Gradient Descent and Stochastic Gradient Descent along with their Nesterov Accelerated Counterparts
Outlier-Detection-Removal-for-the-Seahorse-Datset
Outlier Detection & Removal for OCR and ECAR Protein Channels in the Seahorse XF dataset.
Rainbow-Pong
Reinforcement-Learning----Monte-Carlo-Reinforce
Making use of Monte Carlo Algorithms with Baselines to solve MAP 2 of the Grid World Problem
Reinforcement-Learning---Actor-Critic
Analyzing how the convergence is affected by different combinations of step sizes for actor (policy) and critic (value) using the Pendulum environmnent. The policy used is a Gaussian Continuous Policy on Kernelized Features
Reinforcement-Learning---Policy-and-Value-Iteration
Making use of Policy Iteration and Value Iteration algorithms to solve a simple MDP problem
Reinforcement-Learning---Q-Learning
Using Q-Learning on MAP 4 of the grid world environment
text_similarity
sush1996's Repositories
sush1996/DDPG_Fetch
Exploring the performance of Prioritized Experience Replay (PER) with the DDPG+HER scheme on the Fetch Robotics Environemnt
sush1996/Outlier-Detection-Removal-for-the-Seahorse-Datset
Outlier Detection & Removal for OCR and ECAR Protein Channels in the Seahorse XF dataset.
sush1996/Rainbow-Pong
sush1996/Reinforcement-Learning---Actor-Critic
Analyzing how the convergence is affected by different combinations of step sizes for actor (policy) and critic (value) using the Pendulum environmnent. The policy used is a Gaussian Continuous Policy on Kernelized Features
sush1996/Acrobot-Policy-Gradients
sush1996/Descent-Algorithms
Exploring convergence trend for Gradient Descent and Stochastic Gradient Descent along with their Nesterov Accelerated Counterparts
sush1996/Reinforcement-Learning----Monte-Carlo-Reinforce
Making use of Monte Carlo Algorithms with Baselines to solve MAP 2 of the Grid World Problem
sush1996/Reinforcement-Learning---Policy-and-Value-Iteration
Making use of Policy Iteration and Value Iteration algorithms to solve a simple MDP problem
sush1996/Reinforcement-Learning---Q-Learning
Using Q-Learning on MAP 4 of the grid world environment
sush1996/text_similarity
sush1996/tgcn2
sush1996/wordify-phone-numbers
Wordifying US phone numbers