Open
Description
Description
Hi, there are two dead links in the "Using RLlib with torch 2.x compile" page on Ray 2.44.1:
The problem is in this paragraph:
For detailed tables, see Appendix. For the benchmarking code, see run_inference_bm.py. To run the benchmark use the following command:
The two links don't work.
Also the link in the paragraph under the "Exploration" section has the same problem:
This benchmark script runs the PPO algorithm with the default model architecture for the Atari-Breakout game. It runs the training for n iterations for both compiled and non-compiled RLModules and reports the speedup. Note that negative speedup values mean a slowdown when you compile the module.
Link
https://docs.ray.io/en/releases-2.44.1/rllib/rllib-torch2x.html#inference