photo

Nicolas CRETIN


Last seen: 2 months 前 |  自 2023 起处于活动状态

Followers: 0   Following: 0

统计学

  • Thankful Level 3
  • First Answer

查看徽章

Feeds

排序方式:

提问


Dealing with delayed observations/reward in RL
Hi everyone, I'm currently facing an issue: my agent can't learn to control the water tank system of the example below if I ad...

3 months 前 | 0 个回答 | 0

0

个回答

已回答
RL: Continuous action space, but within a desired range（use PPO)
Hi Peijie, I'll create a new answer! As said here (Proximal policy optimization (PPO) reinforcement learning agent - MATLAB -...

3 months 前 | 0

已回答
RL: Continuous action space, but within a desired range（use PPO)
Hello, I'm quite beginner in this field, but I faced the same issue and I used a sigmoïd layer and then a scaling layer to by...

4 months 前 | 0

提问


Unrecognized property 'LearningFrequency' for class 'rl.option.rlPPOAgentOptions'.
Hello everbody, I'm facing the following error: Unrecognized property 'LearningFrequency' for class 'rl.option.rlPPOAgentOp...

4 months 前 | 1 个回答 | 0

1

个回答

提问


Tuning ExperienceHorizon hyperparamter for PPO agent (Reinforcement Learning)
Hello everyone, I'm trying to train a PPO agent, and I would like to change the value for the ExperienceHorizon hyperparameter...

4 months 前 | 1 个回答 | 0

1

个回答

提问


Trying to train PPO RL agent
Hello, I'm trying to train a PPO agent, but I'm encountering the following issue: From a certain time, the agent don't learn ...

4 months 前 | 1 个回答 | 0

1

个回答

提问


Debug mode for RL agent networks
Is there any way to enter debug mode, to see what is happening inside the RL agent nets while training is running? Some of my...

5 months 前 | 1 个回答 | 0

1

个回答

提问


Can we set programmatically parameters of 'Permanent Magnet Synchronous Machine' block?
Hello, Does anyone know how to set programmatically parameters inside this BLDC motor block (like the initial condition for ex...

5 months 前 | 1 个回答 | 0

1

个回答

提问


How can we analyse learning curves (of reinforcement learning agent training) to predict what is wrong with the design of our network/reward function?
Hi everyone, I'm trying to train a PPO (continuous) agent, and I have some general questions about reinforcement learning: Ho...

6 months 前 | 1 个回答 | 0

1

个回答

已回答
get the error "For deep learning, the simulation target language must be set to C++" while running the evaluatePolicy function automatically generated by Matlab
I've finally found the answer to my question on this post: For deep learning, the simulation target language must be set to C+...

6 months 前 | 0

| 已接受

提问


Is there a way to visualize simulation result (after RL agent training) at the command line?
Hi! Is there any way to visualize the result of a simulation at the command line, given a simulation result (as on the followin...

7 months 前 | 1 个回答 | 0

1

个回答

提问


get the error "For deep learning, the simulation target language must be set to C++" while running the evaluatePolicy function automatically generated by Matlab
Hello everyone! I trained a RL agent (PPO actor-critic agent), then I generated the evaluatePolicy() function with the generate...

7 months 前 | 1 个回答 | 0

1

个回答

提问


why is NaN not of 'NaN type' in Simulink?
Hi everyone, Please, could anyone explain why the constant block NaN is not of type NaN? Thank you in advance! Best regar...

7 months 前 | 2 个回答 | 0

2

个回答

已回答
Error using medicalref3d/intrinsicToWorld Invalid argument at position 2. Value must be integer.
Hi kam! Is that your question: You're trying to run this example (this line only works if you have at least Matlab R2022b): ...

9 months 前 | 0

提问


Active rotation with quaternions: from initial orientation given with Euler angles get the new orientation after an active rotation described by the qr quaternion.
Hello everyone! I'm sorry to be so verbose, but I'm quite sure my question will help others too. My aim is to create a get_r...

9 months 前 | 1 个回答 | 0

1

个回答

提问


Create neural network to predict global pattern of a misspelled word (input) with 2 categorical strings as outputs
Hi Matlab staff ! I'm trying to create a neural network that detect misspelling in a single word given as input. I have only tw...

1 year 前 | 1 个回答 | 0

1

个回答