I have been experimenting with the partially observable StatelessCartPole and different options on how to deal with it, very similar to what @sven1977 did in this Anyscale blog post . Currently, I am struggling to reproduce similar results; PPO does not seem to learn on StatelessCartPole - neither w…

LSTM and Attention on Stateless CartPole

stefanbschneider November 30, 2021, 1:34pm 3

@mannyv Thanks, I’ll keep following these issues and look for other related bugs. I’m using ray 1.8.0

Topic		Replies	Views
Frame Stacking W/ Policy_Server + Policy_Client RLlib	17	954	May 29, 2023
How to using self-definded tensor as padding observations for LSTM/Attention models RLlib	8	626	May 19, 2021
Custom model with LSTM crashes PPO sampler.py RLlib	0	269	November 24, 2023
There was an error changing the trajecy_tory_view_api into continuous action space RLlib	7	600	February 22, 2022
Issue with custom LSTMs RLlib	34	2166	February 26, 2023