[UA] NaUKMA RL Spring '24, Lecture/Practice 5 - Actor-Critics
ฝัง
- เผยแพร่เมื่อ 11 ต.ค. 2024
- A2C, policy-based actor, value-based critic, TD error in AC, advantage function.
Panda-Gym, Stable-baselines3, A2C on PandaReachDense-v3, observation normalization.
![[UA] NaUKMA RL Spring '24, Practice 6 - Paper breakdown: Genie from DeepMind](http://i.ytimg.com/vi/alj9isaGUko/mqdefault.jpg)
![[UA] NaUKMA RL Spring '24, Practice 6 - Paper breakdown: Genie from DeepMind](/img/tr.png)
