PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Major Project
Reinforcement Learning with OpenAI Gym
Q-learning and DQN agents trained on Gymnasium environments
3-4 weeks build
Overview
A structured tour of reinforcement learning on Gymnasium, the maintained successor to OpenAI Gym. Tabular Q-learning and SARSA solve FrozenLake and Taxi, then a DQN with experience replay and a target network tackles CartPole and LunarLander. Every agent logs to TensorBoard, and the report compares learning curves, stability and the effect of each hyperparameter.
What makes it stand up
- 01Tabular Q-learning and SARSA on discrete environments
- 02DQN with replay buffer and target network
- 03Double DQN variant for comparison
- 04TensorBoard logging of rewards and losses
- 05Hyperparameter study on learning rate, gamma and epsilon
Module breakdown
- 01
Environment wrapper
Common interface and seeding across Gymnasium tasks.
- 02
Tabular agents
Q-learning and SARSA with epsilon-greedy policies.
- 03
Deep agents
DQN and Double DQN in PyTorch.
- 04
Experiments
Scripted runs over seeds and hyperparameters.
- 05
Visualisation
Learning curves and recorded episode videos.
After this, you will be able to
- Explain on-policy versus off-policy learning with SARSA and Q-learning
- Defend why DQN needs replay and a target network
- Demo a trained LunarLander agent landing live
Technology stack
- Python
- Gymnasium
- PyTorch
- NumPy
- TensorBoard
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support