This assignment deals topics such as reinforcement learning and Markov Decision Processes. Questions as well as responses are written in LaTeX
.
Covers DFS, BFS, Best First Search and A* Search. Also covers admissibility and consistency.
Covers the concepts of reinforcement learning. Uses A* Search.
Determine optimal policy
Implements a basic Q-Learning algorithm for FrozenLake
environment assuming
Process text corpus of movie review and use Singular Value Decomposition (SVD) to generate word vectors, and compare with Word2Vec
from gensim
on basis of cosine-similarity.