photo

Tech Logg Ding


Last seen: 2 years ago |  Active since 2020

Followers: 1   Following: 0

Statistics

  • Thankful Level 3

View badges

Feeds

View by

Question


Modify Reinforcement Learning Algorithm
Hi all, I am looking for way to change the actor's objective function according to a paper (https://cs-people.bu.edu/rmancuso/...

2 years ago | 1 answer | 0

1

answer

Question


Reinforcement Learning - Access agent/training parameters while training
Hi, I am writing to ask if there's anyway to access the agent or the training statistics during the training process? For exa...

3 years ago | 1 answer | 0

1

answer

Question


Parallel computing for Reinforcement Learning training on VM
Hi, I am writing to ask if there's a way to increase the number of vCPU assigned to a worker when using parallel training for ...

3 years ago | 0 answers | 0

0

answers

Question


Soft Actor Critic deploy mean path only
Hi, I'm wondering if there's a way to only deploy the mean path of the SAC agent after it's been trained? This is useful to crea...

3 years ago | 1 answer | 0

1

answer

Question


Reinforcement Learning Training Algebraic Loop Delay Blocks
Hi all, I set up a RL training with a simscape model and I needed to use delay blocks to avoid algebraic loop. However, this c...

3 years ago | 0 answers | 0

0

answers

Question


Simcape two phase fluid custom component
I am trying to write a custom component for a non-isentropic compressor in Simscape. However, I saw a convection term that I don...

3 years ago | 1 answer | 0

1

answer

Question


Bipedal walking robot TD3 training example bad convergence
Hi all, I have attempted to run the bipedal walking robot example training myself and it converged to an suboptimal solution. ...

3 years ago | 0 answers | 0

0

answers

Question


SAC agent actor network setup and action generation
Hi, I'm trying to develop a SAC agent for continuous control task with 2 actions. The agent's explored actions looks like this: ...

3 years ago | 1 answer | 1

1

answer

Question


How does RL algorithm work with RNNs?
Hi, I noticed that Matlab 2021a allows users to use RL algorithms, such as DDPG, with RNN in the deep neural network structure...

4 years ago | 1 answer | 0

1

answer

Question


Reinforcement Learning Toolbox RAM increment
When I am running trainings using the Reinforcement Learning Toolbox, I noticed that the RAM usage increases significantly as th...

4 years ago | 1 answer | 0

1

answer

Question


Reinforcement Learning Memory Error
When I turn on the SaveExperienceBufferWithAgent, I get the following error: Warning: Unable to save the agent to the director...

4 years ago | 0 answers | 0

0

answers

Question


Reinforcement Learning Noise Model Mean Attraction Constant
What does the mean attraction constant do? How can I tune it properly to promote exploration and learning? I can't seem to get t...

4 years ago | 1 answer | 0

1

answer

Question


Reinforcement Learning experience buffer length and parallelisation toolbox
When parallelisation is used when training a DDPG agent with the following settings: trainOpts.UseParallel = true; trainOpts.P...

4 years ago | 1 answer | 0

1

answer

Question


Reinforcement learning DDPG action fluctuations
Upon attempting to train the path following control example in MATLAB, the training process generated the behviour shown in the ...

4 years ago | 1 answer | 0

1

answer

Question


DDPG multiple action noise variance error
Hi, I am working on developing an adaptive PID for a water tank level controller shown here: The outputs of the RL Agent b...

4 years ago | 0 answers | 0

0

answers

Question


2P-MA Heat Exchanger Block Not Stable
Hi, I have recently attempted to implement the 2P-MA heat exchanger block in the Simscape Fluids toolbox and the results were ve...

4 years ago | 1 answer | 0

1

answer

Question


Simscape Two-phase Fluid Constant Pressure Specific Heat
In the two_phase_fluid.ssc domain file (located in: C:\Program Files\MATLAB\R2020a\toolbox\physmod\simscape\library\m\+foundatio...

4 years ago | 1 answer | 0

1

answer