Course Implementations & Demos
Demo animation
will go here
RL FOUNDATIONS
GridWorld Value Iteration
Tabular value iteration and policy visualization (Module 2)
Coming soonDemo animation
will go here
DEEP RL
CartPole with DQN
DQN variations using Stable-Baselines3 (Module 3)
Coming soonDemo animation
will go here
POLICY GRADIENTS
PPO on MiniGrid
Proximal Policy Optimization implementation (Module 4)
Coming soonDemo animation
will go here
LANGUAGE MODELS
RLHF for Toy LLM
Preference collection and reward model training (Module 7)
Coming soonDemo animation
will go here
OFFLINE RL
Decision Transformer
Sequence modeling approach implementation (Module 8)
Coming soonDemo video
will go here
MODEL-BASED RL
DreamerV3 World Model
World model learning and planning (Module 9)
Coming soonDemo animation
will go here
HIERARCHICAL RL
Hierarchical RL Agent
Options framework implementation (Module 10)
Coming soonDemo animation
will go here
MULTI-AGENT RL
PettingZoo Multi-Agent
Cooperative and competitive agent training (Module 12)
Coming soonDemo video
will go here
ROBOTICS
Sim2Real Transfer
PyBullet/MuJoCo simulation to real world (Project 3)
Coming soon