Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Thank you very much for the clarification; I really appreciate it. @salvododo
salvododo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
What I mean is that you might simply want to generate actions (e.g., new slicing profile) deterministically so that you can cover all state/action transitions you need. You want to at least cover a...
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @salvododo, thank you very much for the information. Could you please share additional details regarding the deterministic policy to cover state transitions exhaustively? I would greatly appreci...
salvododo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
I don't think the ticketing system for Colosseum is the right platform for this. If your goal is to generate datasets and cover state transitions exhaustively, I suggest you follow this https://ope...
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @salvododo, Thank you for the clarification; I understand now. Since we’re also part of the PAWR project, I’ve posted a similar question on the Colosseum desktop waiting for response. I’d like t...
salvododo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Oh, I see. Sorry but it's been a long time since we published this and I completely forgot. The dataset only includes static policies for each experiment. The dynamic part is performed in testing w...
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @salvododo, I very much appreciate your detailed explanations. I have another issue. For example, in file `rome_static_close\tr0\exp1\bs1\slices_bs1\1010123456002_metrics.csv` for UE2, the total...
salvododo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
I would say you can likely select one scheduler (PF should be fine), and then split the CSV files based on slicing policies. The data logging resolution is 250ms, and what you see is the unix tim...
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @salvododo, thank you for sharing the details. It’s great to hear that the Communications Magazine dataset can be used for DRL training. Since I would like to train the slicing policy instead o...
salvododo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
you can use that to build a state/action transition, yes. See "Dynamic slice resizing" to understand how slicing policies change over time to build a partial MDP
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @salvododo, thank you for your response. I have two questions as follows. 1. What about this dataset https://github.com/wineslab/colosseum-oran-commag-dataset 2. Is there any available dataset...
salvododo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi, this dataset is primarily tailored at training with tabular data. Since all data is collected using a static policy, you won't have a full MDP with transitions like you want. You only state tra...
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @salvododo, is it possible to form trajectories like <1st-row state, 1st-row action, 1st-row reward, 2nd-row next state>, <2nd-row state, 2nd-row action, 2nd-row reward, 3rd-row next state>, and...
hanghoo created a comment on an issue on wineslab/colosseum-oran-coloran-dataset
Hi @gicu8ab2, do you get any progress on this?