photo

Heesu Kim


Last seen: 대략 3년 전 |  2021년부터 활동

Followers: 0   Following: 0

통계학

  • Thankful Level 2
  • Thankful Level 1

배지 보기

Feeds

보기 기준

질문


Oscillation of Episode Q0 during DDPG training
How do I interpret this kind of Episode Q0 oscillation? The oscillation shows a pattern like up and down and the range also i...

3년 초과 전 | 답변 수: 0 | 0

0

답변

질문


Do the actorNet and criticNet share the parameter if the layers have the same name?
Hi. I'm following the rlDDPGAgent example, and I want to make sure one thing as in the title. At the Create DDPG Agent Using I...

3년 초과 전 | 답변 수: 1 | 0

1

답변

질문


Any RL Toolbox A3C example?
Hi. I'm currently trying to implement an actor-critic-based model with pixel input on the R2021a version. Since I want to co...

3년 초과 전 | 답변 수: 1 | 0

1

답변

질문


Why does the RL Toolbox not support BatchNormalization layer?
Hi. I'm currently trying DDPG with my own network. But when I try to use BatchNormalizationLayer, the error message says Batch...

3년 초과 전 | 답변 수: 3 | 0

3

답변

질문


How to build an Actor-Critic model with shared layers?
Hi. I'm trying to build an Actor-Critic model uisng Reinforcement Learning Toolbox. What I'm currently intending is to share l...

3년 초과 전 | 답변 수: 0 | 0

0

답변