Back to Home

Samrat Kar

exploring & experimenting

Introduction to Reinforcement learning using Gymnasium

December 28, 2025
gymnasium reinforcement-learning rl python 



import gymnasium as gym

# Create an environment
env = gym.make('CartPole-v1')

# Initialize the environment
state = env.reset()

# Example of taking an action
action = env.action_space.sample()
next_state, reward, done, info = env.step(action)

env = create_environment()
state = env.get_initial_state()
for i in range (n_iterations):
   action = choose_action(state)
   state, reward = env.execute (action)
   update_knowledge(state, action, reward)

Tasks -

  1. episodic - tasks segmented into episodes. episode has a beginning and an end.
  2. continuous

Key points

  1. RL is based on reward for desirable behaviors and punishments for undesirable ones.
  2. RL is based on interaction between an agent and an environment, to achieve a specific goal.