Sayak Kundu

macro_tiles_10x10 has 100 macros. So you have to update the "sequence_length" to 101 in [train_ppo.py](https://github.com/google-research/circuit_training/blob/d5e454e5bcd153a95d320f664af0d1b378aace7b/circuit_training/learning/train_ppo.py#L57) and "max_sequence_length" to 101 in [ppo_collect.py](https://github.com/google-research/circuit_training/blob/d5e454e5bcd153a95d320f664af0d1b378aace7b/circuit_training/learning/ppo_collect.py#L53) before starting the training. "sequence_length" and "max_sequence_length" should be...

By default plc_client computes the total area of macros and soft macros and then create a square canvas with 60% utilization. If you want to use different canvas size you...

In the [FAQ](https://github.com/google-research/circuit_training/tree/d5e454e5bcd153a95d320f664af0d1b378aace7b/circuit_training/grouping#faq) section of Circuit-Training/grouping/README I found "We assume that a netlist that has all its nodes already placed. It does not have to be a good placement. A...

You can find the details about the proxy cost computation [here](https://docs.google.com/document/d/1hM7UbmANkhoGB3-UfFBp8TRDvvVjpmio7cyyjK4a5bI/edit). ------------------------------------------------------------------------------------------------------------------------------- You may check out our [MacroPlacement](https://github.com/TILOS-AI-Institute/MacroPlacement) repo. We provide a [script](https://github.com/TILOS-AI-Institute/MacroPlacement/blob/main/Flows/util/gen_pb.tcl) to write out the protobuf netlist from...

Hi @vvbandeira , I have incorporated all the suggested changes. Can you please check and Let me know if anything is missing.