training.py

for e in tqdm(range(0, num_of_episodes)):
    # Reset the enviroment
    state = enviroment.reset()

    # Initialize variables
    reward = 0
    terminated = False

    for timestep in range(timesteps_per_episode):
        state = img_processor.process_env_state(state)

        # Run Action
        action = agent.act(state)

        # Take action    
        next_state, reward, terminated, info = enviroment.step(action) 
        next_state = img_processor.process_env_state(next_state)

        agent.store(state, action, reward, next_state, terminated)

        state = next_state

        if terminated:
            agent.alighn_target_model()
            break

        if len(agent.expirience_replay) > batch_size:
            agent.retrain(batch_size)