Feeds
質問
为什么我的强化学习奖励一直不收敛 - Why do my reinforcement learning rewards fail to converge?
我是在用simulink和Amesim进行联合仿真,但是奖励一直不收敛,我试过调小Actor和critic学习率到0.0001,但是没用 I am performing co-simulation using Simulink and Amesim,...
約13時間 前 | 0 件の回答 | 0
0
回答質問
Why does an algebraic loop occur in my Simulink model (specifically involving an `isdone` block)?
我的T_cabin是从Amesim中返还的座舱温度,我本意是想将这个SAC智能体的Isdone设置为T_cabin小于5℃时终止训练,但是我不知道为什么这个模块明明不存在除0和积分环节也会存在代数环? My `T_cabin` value—the cab...
7日 前 | 0 件の回答 | 0
0
回答質問
Why does an algebraic loop appear in my Simulink model?
我的T_cabin是从amesim中返回的数据,我运行amesim完全是没问题的,但是我不知道为什么在simulink会出现这样的代数环,而且当我调小求解器的相对容差之后就可以正常运行了,这是为什么? Google Translate: T...
8日 前 | 1 件の回答 | 0
1
回答質問
How to achieve joint simulation of Simulink and Amesim
Which methods can be used for the joint simulation of Simulink and Amesim?
25日 前 | 0 件の回答 | 0
0
回答質問
How to build an automotive HVAC system in Simulink? 如何用Simulink建立一个包含冷凝器,膨胀阀,蒸发器的汽车HVAC系统?
制冷剂在经过压缩机,冷凝器,膨胀阀,蒸发器的时候要经历一个什么样的过程,然后如何得出最后汽车座舱的温度呢? (Google Translate:) What process does the refrigerant undergo as it pass...
約1ヶ月 前 | 2 件の回答 | 0
2
回答回答済み
Why can‘t I run my Simulink model after training my reinforcement-learning agent
Just now, I adjusted some of the solvers in Simulink. I changed the zero-crossing control from "using local control" to "fully d...
Why can‘t I run my Simulink model after training my reinforcement-learning agent
Just now, I adjusted some of the solvers in Simulink. I changed the zero-crossing control from "using local control" to "fully d...
約1ヶ月 前 | 0
| 採用済み
質問
Why can‘t I run my Simulink model after training my reinforcement-learning agent
我训练完了我的强化学习智能体之后再返回simulink模型,我正准备用训练好的agent来测试一下性能,但是我的simulink模型居然连100s都跑不完了,一直卡在这个界面,这是为什么? (Google Translate:) After train...
約2ヶ月 前 | 1 件の回答 | 0