Artificial Intelligence Asked on November 10, 2021
I am writing a couple of different reinforcement learning models based on Rainbow DQN or some PG models. All of them internally use an LSTM network because my project is using time series data.
I wanted to test my models using OpenAI Gym before I add too many domain specific code to the models.
The problem is that, all of the Atari games seem to fall into the CNN area which I don’t use.
Is it possible to use OpenAI Gym to test any time series data driven RL models/networks?
If not, is there any good environment that I can use to examine the validity of my models?
If I understand your problem correctly, you can test on just about any environment, and just omit parts of the observations to ensure your RNN is learning. For example, you can test on cartpole, ignoring the velocity and angular velocity states. This way the MDP isn't actually Markovian and you'll need the RNN to learn.
Answered by harwiltz on November 10, 2021
1 Asked on September 10, 2020 by tmt
0 Asked on September 9, 2020 by foxcharles
1 Asked on September 7, 2020 by shashank-gargeshwari
1 Asked on August 30, 2020 by toben-aus
0 Asked on August 22, 2020 by nick
1 Asked on August 16, 2020 by moe-kaung-kin
1 Asked on August 9, 2020 by ray-walker
0 Asked on August 1, 2020 by green_wizard
0 Asked on July 26, 2020 by dae-young-park
1 Asked on July 21, 2020 by datdinhquoc
Get help from others!