Method act

humanoidverse/agents/modules/ppo_modules.py:67–69

(self, actor_obs, **kwargs)

        self.distribution = Normal(mean, mean*0. + self.std)

    def act(self, actor_obs, **kwargs):
        self.update_distribution(actor_obs)
        return self.distribution.sample()
    
    def get_actions_log_prob(self, actions):
        return self.distribution.log_prob(actions).sum(dim=-1)