It targets an AlpaSim user rather than an AlpaSim developer It treats docker compose as the primary execution environment. It focuses on letting the user do simple things quick and leaves detail for ...
Configure and run a full RL pipeline using the cookbook's RL abstractions with `RLDatasetBuilder`. In tutorials 05-06 you wrote RL loops manually. The cookbook also provides `rl.train.Config` + ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results