Daniel Seita

Another related question is if there are some example scripts that show how to save, and then resume training, from a given snapshot. I didn't see any but I am...

Saving and loading is really easy. Here's example_1 showing how to train normally, and in particular, building the algorithm and the agent. https://github.com/astooke/rlpyt/blob/75e96cda433626868fd2a30058be67b99bbad810/examples/example_1.py#L36-L37 To load a pre-trained model, which ideally...

Another thing I forgot to mention is that you need to be careful about the epsilon, the exploration schedule. However, if you load the `itr` variable I think that should...

Thanks @MandiZhao and @astooke . Indeed if `getattr(env_info, "traj_done", d) = True`, then for games that have lives (e.g., Breakout) that will trigger when the agent loses all lives and...

Hi @astooke I think I am able to get this implemented *assuming the CPU sampler*. I'm currently doing this after every "done" but it should be easy to change it...

@astooke After looking at the code a bit more carefully, the GPU sampler is a bit more complex, for two reasons. As you pointed out, this calls the agent's reset_one....

Update September 2020: the file doesn't accept `--tier` as an argument. Pass in the appropriate tier based on the `cfg/` file. In the cfg file, you can change the `num_width_points`...

**Update October 2020**: the three files: ``` demos-2020-02-09-16-31-pol-oracle-seed-1336_to_1340-obs-blender-depth-False-rgbd-True-tier1_epis_2000_COMBO.pkl demos-2020-02-10-15-02-pol-oracle-seed-1336_to_1340-obs-blender-depth-False-rgbd-True-tier2_epis_2000_COMBO.pkl demos-2020-02-10-15-05-pol-oracle-seed-1336_to_1340-obs-blender-depth-False-rgbd-True-tier3_epis_2000_COMBO.pkl ``` are available on the project website for download: https://sites.google.com/view/fabric-smoothing/home

That's a mistake/typo on my part. I'll fix it soon.

Not to mention DDPG ...