91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

  • 大小: 5.41MB
    文件類型: .zip
    金幣: 2
    下載: 0 次
    發布日期: 2023-11-18
  • 語言: Python
  • 標簽:

資源簡介

深度增強學習算法的PyTorch實現(策略梯度/生成對抗模仿學習)

資源截圖

代碼片段和文件信息

import?torch


def?a2c_step(policy_net?value_net?optimizer_policy?optimizer_value?states?actions?returns?advantages?l2_reg):

????“““update?critic“““
????values_pred?=?value_net(states)
????value_loss?=?(values_pred?-?returns).pow(2).mean()
????#?weight?decay
????for?param?in?value_net.parameters():
????????value_loss?+=?param.pow(2).sum()?*?l2_reg
????optimizer_value.zero_grad()
????value_loss.backward()
????optimizer_value.step()

????“““update?policy“““
????log_probs?=?policy_net.get_log_prob(states?actions)
????policy_loss?=?-(log_probs?*?advantages).mean()
????optimizer_policy.zero_grad()
????policy_loss.backward()
????torch.nn.utils.clip_grad_norm_(policy_net.parameters()?40)
????optimizer_policy.step()

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\
?????文件????????2291??2019-04-25?22:23??PyTorch-RL-master\README.md
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\assets\
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\assets\expert_traj\
?????文件?????5600610??2019-04-25?22:23??PyTorch-RL-master\assets\expert_traj\Hopper-v2_expert_traj.p
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\assets\learned_models\
?????文件??????298897??2019-04-25?22:23??PyTorch-RL-master\assets\learned_models\Hopper-v2_ppo.p
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\core\
?????文件?????????729??2019-04-25?22:23??PyTorch-RL-master\core\a2c.py
?????文件????????5430??2019-04-25?22:23??PyTorch-RL-master\core\agent.py
?????文件?????????841??2019-04-25?22:23??PyTorch-RL-master\core\common.py
?????文件????????1032??2019-04-25?22:23??PyTorch-RL-master\core\ppo.py
?????文件????????4672??2019-04-25?22:23??PyTorch-RL-master\core\trpo.py
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\examples\
?????文件????????5294??2019-04-25?22:23??PyTorch-RL-master\examples\a2c_gym.py
?????文件????????6590??2019-04-25?22:23??PyTorch-RL-master\examples\ppo_gym.py
?????文件????????5406??2019-04-25?22:23??PyTorch-RL-master\examples\trpo_gym.py
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\gail\
?????文件????????7699??2019-04-25?22:23??PyTorch-RL-master\gail\gail_gym.py
?????文件????????2531??2019-04-25?22:23??PyTorch-RL-master\gail\save_expert_traj.py
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\models\
?????文件?????????902??2019-04-25?22:23??PyTorch-RL-master\models\mlp_critic.py
?????文件?????????905??2019-04-25?22:23??PyTorch-RL-master\models\mlp_discriminator.py
?????文件????????2426??2019-04-25?22:23??PyTorch-RL-master\models\mlp_policy.py
?????文件????????1702??2019-04-25?22:23??PyTorch-RL-master\models\mlp_policy_disc.py
?????目錄???????????0??2019-04-25?22:23??PyTorch-RL-master\utils\
?????文件?????????139??2019-04-25?22:23??PyTorch-RL-master\utils\__init__.py
?????文件?????????371??2019-04-25?22:23??PyTorch-RL-master\utils\math.py
?????文件?????????862??2019-04-25?22:23??PyTorch-RL-master\utils\replay_memory.py
?????文件?????????126??2019-04-25?22:23??PyTorch-RL-master\utils\tools.py
?????文件????????1949??2019-04-25?22:23??PyTorch-RL-master\utils\torch.py
............此處省略1個文件信息

評論

共有 條評論