All code I did at MIPT as part of my reinforcement learning course

1. Solved Mountain Car problem

2. Solved Cartpole problem

3. Cross-Entropy Method with Neural Networks

• Implemented cross-entropy method for discrete environments (CartPole-v1)
• Applied basic neural network policies for continuous control

4. Reinforcement Learning with PyTorch

• Policy gradient methods using PyTorch neural networks
• Neural network-based policy for CartPole environment
• 

5. Cross-Entropy Method with Scikit-learn MLP

• Cross-entropy method implementation using scikit-learn MLPRegressor
• Multi-layer perceptron for policy approximation
• 
• 

• faran.py - Cross-entropy method implementation for discrete environments
• Basic_RL.ipynb - Basic RL algorithms and environment solving
• Crossentropy_method_&_Neural_Nets_Sklearn_MLP.ipynb - Cross-entropy method with scikit-learn MLP
• RL_with_Neural_Nets_Pytorch.ipynb - PyTorch-based neural network RL implementations

gymnasium numpy matplotlib torch pandas scikit-learn