Tabular methods for reinforcement learning

This repo implements Deep Q-Network (DQN) for solving the Cliff Walking v0 environment of the Gymnasium library using Python 3.8 and PyTorch 2.0.1 with the finest tuning.

Simple implementation and comparison of three reinforcement learning models.

This project utilizes Markov Decision Process (MDP) principles to implement a custom "CliffWalking" environment in Gym, employing policy iteration to find an optimal policy for agent navigation.

AI related graph search algorithms with step-by-step implementation as well as comparison between different methods for cliff-walker problem.

Built a Reinforcement Learning project on the Cliff Walking Problem using SARSA and Q-Learning with Gymnasium. Compared on-policy vs off-policy learning, showing how SARSA learns safer paths while Q-Learning finds optimal but riskier routes.

Cliffwalk to compare SARSA and Q-Learning

Cliff Walking Project: An implementation of classic MDP algorithms (Policy Iteration, Value Iteration)

simple cliff walk implementation

AI application of Min-Max algorithm including alpha-beta pruning approach for two agents in cliff-walker scenario

Temporal Difference methods - A simple implementation of SARSA algorithm applied to OpenAI gym's "CliffWalking" environment.

Use cliff walking to compare the difference between Q-learning and SARSA algorithms in Reinforcement Learning

Solutions for Reinforcement learning lab-exam 2019

Reinforcement Learning basic tasks

🧗 Navigates a grid-world environment using SARSA Reinforcement Learning. Features on-policy path optimization.