MarcoMeter/recurrent-ppo-truncated-bptt
Baseline implementation of recurrent PPO using truncated BPTT
Jupyter NotebookMIT
Issues
- 3
Question Regarding Sequence Length
#17 opened by Davide236 - 7
Pre-trained Models Do Not Work
#14 opened by WilliamYue37 - 0
- 4
Excuse me,how enjoy the model “./models/cartpole_masked.nn”? When I run enjoy.py , Show "RuntimeError: expected scalar type Double but found Float "
#9 opened by jialuyu61 - 7
Can this repo train continuous environments?
#8 opened by 1900360 - 8
Masked mean for advantage normalization?
#10 opened by finnBsch - 2
about sequence_length
#11 opened by xixiha5230 - 6
- 3
- 5
- 8
Adapting the repo to my specific problem
#3 opened by VVIERV00