Load a pretrained neural network object in rlNeuralNetworkEnvironment

Question

Vasu Sharma 2023-11-21

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2050202-load-a-pretrained-neural-network-object-in-rlneuralnetworkenvironment

回答： Emmanouil Tzorakoleftherakis 2023-12-21

Hi,

I want to train an RL MBPO Agent that samples from a model. The model is a trained DL object, trained in matlab. I am wondering how I can load its weights inside the env object. The examples for rlNeuralNetworkEnvironment can be used to define a network structure but I would like to add my weights to this?

Best Regards,

Vasu

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Emmanouil Tzorakoleftherakis 2023-12-21

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2050202-load-a-pretrained-neural-network-object-in-rlneuralnetworkenvironment#answer_1375747

Hi Vasu,

You can use a pretrained environment model with MBPO agent as follows:

1) Create a rlContinuousDeterministicTransitionFunction with the trained dlnet if it is deterministic or rlContinuousGaussianTransitionFunction if it is stochastic (mean heads and std heads).

2) After that, you need to create rlNeuralNetworkEnvironment with newly defined function from 1.

3) Create MBPO agent.

4) Set LearnRate = 0 in TransitionOptimizerOptions in rlMBPOAgentOptions to avoid updating the models during training.

Hope this helps