-
Datargy
- NYC, New York
- in/max-lytovka
Highlights
- Pro
Pinned Loading
-
Thesis_X-CLIP
Thesis_X-CLIP PublicThis is the folder for my thesis paper. The PDF file of the paper is included.
Python 1
-
Computer-Vision_Gesture-Classification
Computer-Vision_Gesture-Classification PublicSegment-based gesture classification using ResNeXt-101 features and lightweight MLPs, trained on the Jester dataset. This project explores frame sampling strategies, MLP architectures, and segment …
Jupyter Notebook
-
Reinforcement-Learning_Temporal-Difference
Reinforcement-Learning_Temporal-Difference PublicExperiments with n-step Temporal Difference learning (Q-learning, SARSA, Expected SARSA) in a Cliff Walking environment, inspired by Sutton & Barto’s Reinforcement Learning.
Python
-
Airbus-Ship-Detection-Challenge
Airbus-Ship-Detection-Challenge PublicThis is the repository for Airbus Ship Detection Challenge on Kaggle
Jupyter Notebook
-
Reinforcement-Learning_Markov-Decision-Process
Reinforcement-Learning_Markov-Decision-Process PublicImplementation of Value Iteration and Q-value Iteration for solving discrete Markov Decision Processes in a maze environment with multiple goals, keys, and doors.
Python
-
Symbolic-AI_Goal-Oriented-Planning-Agent
Symbolic-AI_Goal-Oriented-Planning-Agent PublicImplementation of a goal-oriented BDI agent in Java that navigates a maze using symbolic reasoning. The agent uses a simplified first-order logic (sfol) for beliefs, goals, and actions, with forwar…
Java
If the problem persists, check the GitHub status page or contact support.


