From 50b792b8bc02fa7ac599b96b20ae25c98742ef96 Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Thu, 9 Oct 2025 23:46:09 +0200 Subject: [PATCH] docs(reforcexy): refine README.md MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Signed-off-by: Jérôme Benoit --- ReforceXY/reward_space_analysis/README.md | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/ReforceXY/reward_space_analysis/README.md b/ReforceXY/reward_space_analysis/README.md index 093331f..d63d4a3 100644 --- a/ReforceXY/reward_space_analysis/README.md +++ b/ReforceXY/reward_space_analysis/README.md @@ -476,14 +476,10 @@ python reward_space_analysis.py \ For production validation, compare synthetic analysis with real trading episodes: -1. **Enable logging** in your ReforceXY config -2. **Run training** to collect real episodes -3. **Compare distributions** using `--real_episodes` - ```shell python reward_space_analysis.py \ --num_samples 100000 \ - --real_episodes ../user_data/models/ReforceXY-PPO/sub_train_BTCUSDT_20231201/episode_rewards.pkl \ + --real_episodes ../user_data/transitions/episode_rewards.pkl \ --output real_vs_synthetic ``` -- 2.43.0