From ed9f9d2753350a14d46e2ad493f2635f05ca5dac Mon Sep 17 00:00:00 2001 From: =?utf8?q?J=C3=A9r=C3=B4me=20Benoit?= Date: Fri, 10 Oct 2025 12:27:16 +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 | 8 ++++---- quickadapter/user_data/strategies/QuickAdapterV3.py | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/ReforceXY/reward_space_analysis/README.md b/ReforceXY/reward_space_analysis/README.md index d63d4a3..79502c7 100644 --- a/ReforceXY/reward_space_analysis/README.md +++ b/ReforceXY/reward_space_analysis/README.md @@ -161,7 +161,7 @@ python reward_space_analysis.py \ # Then compare: python reward_space_analysis.py \ --num_samples 100000 \ - --real_episodes ../user_data/transitions/*.pkl \ + --real_episodes path/to/episode_rewards.pkl \ --output real_vs_synthetic ``` @@ -315,7 +315,7 @@ _Invariant / safety controls:_ - Path to real episode rewards pickle file for distribution comparison - Enables distribution shift analysis (KL(synthetic‖real), JS distance, Wasserstein distance, KS test) -- Example: `../user_data/models/ReforceXY-PPO/sub_train_SYMBOL_DATE/episode_rewards.pkl` +- Example: `path/to/episode_rewards.pkl` **`--pvalue_adjust`** (choice: none|benjamini_hochberg, default: none) @@ -383,7 +383,7 @@ python reward_space_analysis.py \ # Real vs synthetic comparison python reward_space_analysis.py \ --num_samples 100000 \ - --real_episodes ../user_data/models/path/to/episode_rewards.pkl \ + --real_episodes path/to/episode_rewards.pkl \ --output validation ``` @@ -479,7 +479,7 @@ For production validation, compare synthetic analysis with real trading episodes ```shell python reward_space_analysis.py \ --num_samples 100000 \ - --real_episodes ../user_data/transitions/episode_rewards.pkl \ + --real_episodes path/to/episode_rewards.pkl \ --output real_vs_synthetic ``` diff --git a/quickadapter/user_data/strategies/QuickAdapterV3.py b/quickadapter/user_data/strategies/QuickAdapterV3.py index 0973ac2..2717763 100644 --- a/quickadapter/user_data/strategies/QuickAdapterV3.py +++ b/quickadapter/user_data/strategies/QuickAdapterV3.py @@ -1243,7 +1243,7 @@ class QuickAdapterV3(IStrategy): f"User denied {trade_direction} {order} for {pair}: " f"close_k[{-k}] {format_number(close_k)} " f"did not break threshold_k[{-(k + 1)}] {format_number(threshold_k)} " - f"(decayed min/max natr_ratio_percent: min={format_number(decayed_min_natr_ratio_percent)}, max={format_number(decayed_max_natr_ratio_percent)})" + f"(decayed natr_ratio_percent: min={format_number(decayed_min_natr_ratio_percent)}, max={format_number(decayed_max_natr_ratio_percent)})" ) return False -- 2.43.0