mbbl
mbbl copied to clipboard
WilsonWangTHU
Hi, Could you make the implementation of SVG public? I have some problem implementing the SVG and hope to refer your repo.
Is there an option to save the learned model and then load it for further training? I did not see any flag for that. Thanks in advance.
Hello, thank you for your hard work in providing and polishing this repository. I would like to replicate the results using Stochastic Value Gradients. I see in the readme that...
Hi, just a minor issue here. The `gym_pendulum` environment in here runs for 201 steps instead of 200 steps as the original gym pendulum does and I think it's because...
Loading the reacher-easy task I received an error about the observation dimensionality (6 vs. 7). The original DeepMind paper states that the observation dimensionality is 7, which is also set...
Thank you so much for provide a Benchmark for Model-Based Reinforcement Learning. I want to modify your code to new version of Gym, I have some question about your code:...
Different algorithms benchmarked in the repo were using different gyms, including the version 0.7.4, 0.10.5 and 0.9.4 To make more fair comparison, should all experiments be done on the same...
