- 1、本文档共37页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Deep Reinforcement Learning_iclr2015
Deep Reinforcement Learning
David Silver, Google DeepMind
Reinforcement Learning: AI = RL
RL is a general-purpose framework for artificial intelligence
I RL is for an agent with the capacity to act
I Each action influences the agent’s future state
I Success is measured by a scalar reward signal
RL in a nutshell:
I Select actions to maximise future reward
We seek a single agent which can solve any human-level task
I The essence of an intelligent agent
Agent and Environment
state
reward
action
at
rt
st I At each step t the agent:
I Receives state st
I Receives scalar reward rt
I Executes action at
I The environment:
I Receives action at
I Emits state st
I Emits scalar reward rt
Examples of RL
I Control physical systems: walk, fly, drive, swim, ...
I Interact with users: retain customers, personalise channel,
optimise user experience, ...
I Solve logistical problems: scheduling, bandwidth allocation,
elevator control, cognitive radio, power optimisation, ..
I Play games: chess, checkers, Go, Atari games, ...
I Learn sequential algorithms: attention, memory, conditional
computation, activations, ...
Policies and Value Functions
I Policy π is a behaviour function selecting actions given states
a = π(s)
I Value function Qπ(s, a) is expected total reward
from state s and action a under policy π
Qπ(s, a) = E
[
rt+1 + γrt+2 + γ
2rt+3 + ... | s, a
]
“How good is action a in state s?”
Approaches To Reinforcement Learning
Policy-based RL
I Search directly for the optimal policy π?
I This is the policy achieving maximum future reward
Value-based RL
I Estimate the optimal value function Q?(s, a)
I This is the maximum value achievable under any policy
Model-based RL
I Build a transition model of the environment
I Plan (e.g. by lookahead) using model
Deep Reinforcement Learning
I Can we apply deep learning to RL?
I Use deep network to represent value function / policy / model
I Optimise value function / policy /model end-to-end
I Using stochastic gradient descent
Bellman Equation
I
您可能关注的文档
- Charmed Meson Production in Proton - (ANTI)PROTON Collisions.pdf
- Charm Results on CP Violation and Mixing.pdf
- Charmonium and CharmSpectroscopyat the e+e- B-Factories.ppt
- chatra kalyan rules.pdf
- chemical priming with urea and KNO3 enhances maiz hybids seed viability under abiotic stress.pdf
- chemical safety of meat products.pdf
- CHATTERBOX BOOK 4(1-2单元).pdf
- Chemical characterization and source apportionment of PM2.5.pdf
- Chemically modified light-curable chitosans with enhanced.pdf
- Chest Ultrasonography in the ICU.pdf
文档评论(0)