Nagi-ovo
Follow
Breezing
135
Followers
17
Followings
Patron
主页
Archives
Portfolios
日寄
PPO
Latest
Hottest
Most Commented
“速通” PPO
Proximal Policy Optimization 终于到了这几年 NLP 领域中比较火热的 RL 算法之一了 On-Policy 算法中,采集数据用的策略和训练的策略是相同的,这样的问题是数据用一次后就得丢弃,然后再重新采集数据,训练速度很慢。 PPO 背后的直觉 …
RL
4 min
9 days ago
Ownership of this blog data is guaranteed by blockchain and smart contracts to the creator alone.
Blockchain ID
#61009
Owner
0x6380302480224d53ec4c2c318d1c7be2c55a7582
Transaction Hash
Creation 0xe99aa0c3...eadd5b56dd
Last Update 0xa2a8e0fd...2a39597ebe
IPFS Address
ipfs://bafkreib6guajxxyr7vuwfe24vb7ndto3kxbond4lbg3cpednsrpqpog3wy