# deep-reinforcement-learning

## deep-reinforcement-learning

- [介绍](https://hujian.gitbook.io/deep-reinforcement-learning/master.md): @gitbook
- [神经网络](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/shen-jing-wang-luo-mo-xing.md)
- [研究平台](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai.md)
- [街机游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/jie-ji-you-xi.md)
- [竞速游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/jing-su-you-xi.md)
- [第一人称射击游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/di-yi-ren-cheng-she-ji-you-xi.md)
- [开放世界游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/kai-fang-shi-jie-you-xi.md)
- [即时战略游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/ji-shi-zhan-lve-you-xi.md)
- [团队体育游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/tuan-dui-ti-yu-you-xi.md)
- [文字冒险游戏](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/wen-zi-mao-xian-you-xi.md)
- [OpenAI Gym & Universe](https://hujian.gitbook.io/deep-reinforcement-learning/qian-yan/yan-jiu-ping-tai/openai-gym-and-universe.md)
- [街机游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi.md)
- [DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/deep-q-network.md)
- [DRQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/deep-recurrent-q-learning.md)
- [Gorila](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/distributed-deep-q-learning.md)
- [Double DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/double-deep-q-learning.md)
- [Prioritized Experience Replay](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/prioritized-experience-replay.md)
- [Dueling DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/dueling-deep-q-network.md)
- [Bootstrapped DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/bootstrapped-deep-q-network.md)
- [Multiagent DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/multiagent-deep-q-network.md)
- [Progressive  Neural Networks](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/progressive-neural-networks.md)
- [A3C](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/asynchronous-deep-reinforcement-learning.md)
- [Retrace(λ)](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/retrace-l.md)
- [ACER](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/actor-critic-with-experience-replay.md)
- [ACKTR](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/actor-critic-using-kronecker-factored-trust-region.md)
- [TRPO](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/trust-region-policy-optimization.md)
- [PPO](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/proximal-policy-optimization.md)
- [UNREAL](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/unreal.md)
- [IMPALA](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/impala.md)
- [Distributional DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/distributional-dqn.md)
- [Noisy-Net](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/noisy-network.md)
- [Rainbow](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/rainbow.md)
- [ES](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/es.md)
- [NS-ES](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/ns-es.md)
- [Deep GA](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/deep-ga.md)
- [Playing Atari with Six Neurons](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/playing-atari-with-six-neurons.md)
- [UCTtoClassification](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/ucttoclassification.md)
- [Policy Distillation](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/policy-distillation.md)
- [Actor-Mimic](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/actor-mimic.md)
- [Action-Conditional Video Prediction](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/action-conditional-video-predictionusing-deep-networks-in-atari-games.md)
- [Self-Supervision](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/loss-is-its-own-reward-self-supervision-for-reinforcement-learning.md)
- [HRA](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jie-ji-you-xi/hra.md)
- [蒙特祖玛的复仇](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou.md)
- [Hierarchical-DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/hierarchical-dqn.md)
- [DQN-CTS](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/unifying-count-based-exploration-and-intrinsic-motivation.md)
- [Pixel Recurrent Neural Networks](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/pixel-recurrent-neural-networks.md)
- [DQN-PixelCNN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/count-based-exploration-with-neural-density-models.md)
- [Ape-X](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/ape-x.md)
- [DQfD](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/dqfd.md)
- [Ape-X  DQfD](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/ape-x-dqfd.md)
- [Natural Language Guided Reinforcement Learning](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ment-te-zu-ma-de-fu-chou/beating-atari-with-natural-language-guided-reinforcement-learning.md)
- [竞速游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jing-su-you-xi.md)
- [Direct Perception](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jing-su-you-xi/deep-driving.md)
- [DDPG](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jing-su-you-xi/ddpg.md)
- [TD3](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/jing-su-you-xi/td3.md)
- [第一人称射击游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/di-yi-ren-cheng-she-ji-you-xi.md)
- [SLAM-Augmented DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/di-yi-ren-cheng-she-ji-you-xi/dqn-with-slam.md)
- [Direct Future Prediction](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/di-yi-ren-cheng-she-ji-you-xi/direct-future-prediction.md)
- [For The Win](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/di-yi-ren-cheng-she-ji-you-xi/for-the-win.md)
- [开放世界游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-shi-jie-you-xi.md)
- [H-DRLN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-shi-jie-you-xi/h-drln.md)
- [Feedback Recurrent Memory Q-Network](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-shi-jie-you-xi/recurrent-memory-q-network.md)
- [Teacher-Student Curriculum Learning](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-shi-jie-you-xi/teacher-student-curriculum-learning.md)
- [即时战略游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi.md)
- [Puppet Search](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/puppet-search.md)
- [Combined Strategic and Tacticals](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/combining-strategic-learning-and-tactical-search-in-real-time-strategy-games.md)
- [Zero Order](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/zero-order.md)
- [IQL](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/iql.md)
- [COMA](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/counterfactual-multi-agent-policy-gradients.md)
- [BiC-Net](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/bic-net.md)
- [Macro-action SL](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/macro-action-sl.md)
- [Macro-action PPO](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/tstarbots.md)
- [On Reinforcement Learning for Full-length Game of StarCraft](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/on-reinforcement-learning-for-full-length-game-of-starcraft.md)
- [AlphaStar](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/ji-shi-zhan-lve-you-xi/alphastar.md)
- [团队体育游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/tuan-dui-ti-yu-you-xi.md)
- [DDPG + Inverting Gradients](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/tuan-dui-ti-yu-you-xi/ddpg-+-inverting-gradients.md)
- [DDPG + Mixing policy targets](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/tuan-dui-ti-yu-you-xi/ddpg-+-mixing-policy-targets.md)
- [Object-centric prediction](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/tuan-dui-ti-yu-you-xi/object-centric-prediction.md)
- [文字冒险游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/wen-zi-mao-xian-you-xi.md)
- [LSTM-DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/wen-zi-mao-xian-you-xi/lstm-dqn.md)
- [DRRN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/wen-zi-mao-xian-you-xi/drrn.md)
- [Affordance Based Action Selection](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/wen-zi-mao-xian-you-xi/affordance-based-action-selection.md)
- [Golovin](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/wen-zi-mao-xian-you-xi/golovin.md)
- [AE-DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/wen-zi-mao-xian-you-xi/ae-dqn.md)
- [开放的挑战](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan.md)
- [游戏通用性](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/you-xi-tong-yong-xing.md)
- [稀疏、延迟、欺骗性的回报](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/xi-shu-3001-yan-chi-3001-qi-pian-xing-de-hui-bao.md)
- [多智能体](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/duo-zhi-neng-ti.md)
- [终身适应](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/kuai-su-shi-ying.md)
- [像人类一样玩游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/xiang-ren-lei-yi-yang-wan-you-xi.md)
- [可调节的性能等级](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/ke-diao-jie-de-xing-neng-deng-ji.md)
- [处理巨大的状态空间](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/chu-li-ju-da-de-zhuang-tai-kong-jian.md)
- [工业界应用](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/gong-ye-jie-ying-yong.md)
- [游戏开发的交互式工具](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/jiao-hu-shi-you-xi-kai-fa.md)
- [创造新的游戏](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/chuang-zao-xin-de-you-xi.md)
- [学习游戏的模型](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/xue-xi-you-xi-de-mo-xing.md)
- [计算资源](https://hujian.gitbook.io/deep-reinforcement-learning/fang-fa/kai-fang-de-tiao-zhan/ji-suan-zi-yuan.md)
- [Distributional RL](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/distributional-rl.md)
- [QR-DQN](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/distributional-rl/qr-dqn.md)
- [Policy Gradient](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/policy-gradient.md)
- [Off-Policy Actor-Critic](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/policy-gradient/off-policy-actor-critic.md)
- [Generalized Advantage Estimation](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/policy-gradient/advantage-estimation.md)
- [Soft Actor-Critic](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/policy-gradient/soft-actor-critic.md)
- [PPO-Penalty](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/policy-gradient/ppo-penalty.md)
- [Model-Based RL](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/model-based-rl.md)
- [I2A](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/model-based-rl/i2a.md)
- [MBMF](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/model-based-rl/mbmf.md)
- [MBVE](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/model-based-rl/mbve.md)
- [World Models](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/model-based-rl/world-models.md)
- [Imitation Learning and Inverse Reinforcement Learning](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/imitation-learning-and-inverse-reinforcement-learning.md)
- [GAIL](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/imitation-learning-and-inverse-reinforcement-learning/gail.md)
- [Transfer and Multitask RL](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/transfer-and-multitask-rl.md)
- [HER](https://hujian.gitbook.io/deep-reinforcement-learning/fu-lu/transfer-and-multitask-rl/her.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://hujian.gitbook.io/deep-reinforcement-learning/master.md?ask=<question>
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.