gym-compete/gym_compete/new_envs/agents/humanoid_blocker.py [29:41]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        reward = forward_reward - ctrl_cost - contact_cost + survive
        # reward = survive

        reward_info = dict()
        reward_info['reward_forward'] = forward_reward
        reward_info['reward_ctrl'] = ctrl_cost
        reward_info['reward_contact'] = contact_cost
        reward_info['reward_survive'] = survive
        reward_info['reward_move'] = reward

        done = bool(qpos[2] <= 0.5)

        return reward, done, reward_info
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



gym-compete/gym_compete/new_envs/agents/humanoid_goalkeeper.py [33:45]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        reward = forward_reward - ctrl_cost - contact_cost + survive

        reward_info = dict()
        reward_info['reward_forward'] = forward_reward
        reward_info['reward_ctrl'] = ctrl_cost
        reward_info['reward_contact'] = contact_cost
        reward_info['reward_survive'] = survive
        reward_info['reward_move'] = reward
        # print("keeper", reward_info)

        done = bool(qpos[2] <= 0.5)

        return reward, done, reward_info
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -