amoudgl / ai-bots

Reinforcement learning and AI algorithms evaluated on OpenAI gym environments

ai-bots

Implementation of several AI and RL algorithms in Python. Evaluation on OpenAI Gym environments.

Implemented Algorithms

• Naive Policy Gradient
• Monte Carlo Policy Gradient with REINFORCE
• Deep Q-Learning with Experience Replay
• Simulated Annealing
• Hill Climbing
• Random Guess