evolve_init.py

if __name__=='__main__':
    #initialize population
    agents = []
    for _ in range(POP_SIZE):
        agent = Policy(obs_dim=NUM_STATES, act_dim=NUM_ACTIONS)
        agents.append(agent)
    
    fitness_list = evaluate_agents(env, agents)
    
    population = pd.DataFrame({'agents': agents,
                               'fitness': fitness_list})
    
    # Sort population dataframe descending by fitness (highest fitness at row 0)
    population = population.sort_values('fitness', ascending=False, ignore_index=True)