Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
XuanCe
Light Logo Dark Logo
XuanCe

教程

  • 安装教程
  • 快速开始
  • 进一步使用
  • 自定义环境
    • 单智能体
    • 多智能体
  • 自定义算法
    • DRL
    • MARL
  • 自定义回调函数

算法:

  • 单智能体强化学习
    • DQN
    • Double DQN
    • Dueling DQN
    • Noisy DQN
    • PER DQN
    • C51
    • QR-DQN
    • DRQN
    • PG
    • NPG
    • A2C
    • PPO-KL
    • PPO-Clip
    • PPG
    • SAC
    • DDPG
    • TD3
    • P-DQN
    • MP-DQN
    • SP-DQN
  • 多智能体强化学习
    • IQL
    • VDN
    • QMIX
    • WQMIX
    • QTRAN
    • DCG
    • IDDPG
    • MADDPG
    • IAC
    • COMA
    • VDAC
    • IPPO
    • MAPPO
    • MFQ
    • MFAC
    • ISAC
    • MASAC
    • MATD3
    • IC3Net
  • 基于模型强化学习
    • DreamerV2
    • DreamerV3
    • HarmonyDream
  • 对比强化学习
    • CURL
    • SPR
    • DrQ
  • 离线强化学习
    • TD3BC

基准

  • 启动基准测试
  • 基准测试结果
    • MuJoCo
    • Atari
    • SMAC
  • 添加新的基准

接口：

  • common
    • tuning_tools
    • callback
    • common_tools
    • memory_offline
    • memory_tools
    • memory_tools_marl
    • offline_util
    • segtree_tool
    • statistic_tools
  • configs
    • Basic Configurations
    • Configuration Examples
    • Custom Configurations
  • environments
    • single_agent_env
      • Gymnasium
      • MiniGrid
      • MetaDrive
      • Gym-Platform
    • multi_agent_env
      • MPE
      • RWARE
      • SMAC
      • Football
      • Drones
      • Magent2
    • vectorization
      • Dummy Vectorization
      • Subprocess Vectorization
      • Basic Class
      • Utils
    • utils
      • Base Class
      • Wrappers
  • torch
    • agents
      • base
      • contrastive_unsupervised_rl
      • core
      • model_based_rl
      • multi_agent_rl
      • offline_rl
      • policy_gradient
      • qlearning_family
    • communications
    • learners
      • learner
      • contrastive_unsupervised_rl
      • model_based
      • multi_agent_rl
      • offline
      • policy_gradient
      • qlearning_family
    • policies
    • representations
    • runners
    • utils
  • tensorflow
    • agents
      • base
      • contrastive_unsupervised_rl
      • core
      • model_based_rl
      • multi_agent_rl
      • offline_rl
      • policy_gradient
      • qlearning_family
    • communications
    • learners
      • learner
      • contrastive_unsupervised_rl
      • model_based
      • multi_agent_rl
      • offline
      • policy_gradient
      • qlearning_family
    • policies
    • representations
    • runners
    • utils
  • mindspore
    • agents
      • base
      • contrastive_unsupervised_rl
      • core
      • model_based_rl
      • multi_agent_rl
      • offline_rl
      • policy_gradient
      • qlearning_family
    • communications
    • learners
      • learner
      • contrastive_unsupervised_rl
      • model_based
      • multi_agent_rl
      • offline
      • policy_gradient
      • qlearning_family
    • policies
    • representations
    • runners
    • utils

玄策开发

  • Github
  • 版本发布日志
  • 贡献指南
  • 文档贡献（英文）
  • 文档贡献（中文）
Back to top
View this page

Offline Reinforcement Learning¶

  • TD3BC : Twin Delayed Deep Deterministic Policy Gradient with Behavior Cloning (TD3BC).

Next
Twin Delayed Deep Deterministic Policy Gradient with Behavior Cloning (TD3BC)
Previous
DrQ: Data-Regularized Q-Learning
Copyright © 2023, XuanCe Contributors.
Made with Sphinx and @pradyunsg's Furo