相关资料
Parallel and Distributed Computation:Numerical Methods:
https://dspace.mit.edu/handle/1721.1/3719#files-areaOpenAI
Gym:
http://arxiv.org/pdf/1606.01540.pdfDQN
https://www.cs.toronto.edu/~vmnih/docs/dqn.pdfDouble
DQN
http://arxiv.org/pdf/1509.06461v3.pdfDPG
http://jmlr.org/proceedings/papers/v32/silver14.pdfDDPG
http://arxiv.org/abs/1509.02971GAE
http://arxiv.org/pdf/1506.02438v4Nervana:
http://www.nervanasys.com/demystifying-deep-reinforcement-learning/David
Silver drl:
http://videolectures.net/site/normal_dl/tag=968058/rldm2015_silver_reinforcement_learning.pdfJohn
Schulman drl:
http://rl-gym-doc.s3-website-us-west-2.amazonaws.com/mlss/2016-MLSS-RL.pdfReinforced
Variational Inference:
http://arkitus.com/files/nips-15-weber-reinforced-inference.pdfGradient
Estimation Using Stochastic Computation Graphs:
https://arxiv.org/pdf/1506.05254.pdfControl
of Memory, Active Perception, and Action in Minecraft:
http://arxiv.org/abs/1605.09128Deep
Reinforcement Learning in Large Discrete Action Spaces:
https://arxiv.org/pdf/1512.07679.pdfDeep
Reinforcement Learning from Self-Play in Imperfect-Information Games:
https://arxiv.org/pdf/1603.01121.pdfContinuous
control with deep reinforcement learning:
http://www0.cs.ucl.ac.uk/staff/d.silver/web/Publications_files/ddpg.pdf