From 860e3d6610b57e8abbb831bf6f7a6c6da0113a95 Mon Sep 17 00:00:00 2001 From: Paul Huliganga Date: Tue, 14 Apr 2026 22:44:22 -0400 Subject: [PATCH] =?UTF-8?q?fix:=20fresh=20PPO=20verbose=3D0=20suppressed?= =?UTF-8?q?=20all=20training=20output=20=E2=80=94=20set=20verbose=3D1?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Without this, Wave 4 scratch-trained models produce no rollout stats in the log, making it impossible to monitor training progress or spot degenerate policies early. Warm-start models in Wave 3 showed stats because verbose=1 was baked into the Phase-2 saved model state; fresh models default to verbose=0. Agent: pi Tests: 96 passed Tests-Added: 0 TypeScript: N/A --- agent/multitrack_runner.py | 2 +- .../autoresearch_phase2_log.txt | 13 +++++++++++++ .../autoresearch_phase3_log.txt | 5 +++++ .../autoresearch_phase4_log.txt | 18 ++++++++++++++++++ 4 files changed, 37 insertions(+), 1 deletion(-) create mode 100644 agent/outerloop-results/autoresearch_phase4_log.txt diff --git a/agent/multitrack_runner.py b/agent/multitrack_runner.py index d99fda9..748f493 100644 --- a/agent/multitrack_runner.py +++ b/agent/multitrack_runner.py @@ -230,7 +230,7 @@ def create_or_load_model(env, learning_rate, warm_start_path=None, seed=None): 'CnnPolicy', env, learning_rate=learning_rate, - verbose=0, + verbose=1, # show rollout stats so training progress is visible in log seed=seed, ) return model diff --git a/agent/outerloop-results/autoresearch_phase2_log.txt b/agent/outerloop-results/autoresearch_phase2_log.txt index 0a1895c..27a0d59 100644 --- a/agent/outerloop-results/autoresearch_phase2_log.txt +++ b/agent/outerloop-results/autoresearch_phase2_log.txt @@ -593,3 +593,16 @@ [2026-04-14 22:40:11] [Champion] 🏆 NEW BEST! Trial 3: mean_reward=90.0000 params={'r': 90} [2026-04-14 22:40:11] [Champion] 🏆 NEW BEST! Trial 5: mean_reward=75.0000 params={'n_steer': 8} [2026-04-14 22:40:11] [AutoResearch] Only 1 results — using random proposal. +[2026-04-14 22:43:59] [AutoResearch] GP UCB top-5 candidates: +[2026-04-14 22:43:59] UCB=2.3107 mu=0.3981 sigma=0.9563 params={'n_steer': 9, 'n_throttle': 2, 'learning_rate': 0.001405531880392808, 'timesteps': 26173} +[2026-04-14 22:43:59] UCB=2.3049 mu=0.8602 sigma=0.7224 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.001793493447174312, 'timesteps': 19198} +[2026-04-14 22:43:59] UCB=2.2813 mu=0.4904 sigma=0.8954 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0011616192816742616, 'timesteps': 13887} +[2026-04-14 22:43:59] UCB=2.2767 mu=0.5194 sigma=0.8787 params={'n_steer': 9, 'n_throttle': 4, 'learning_rate': 0.0011646447444663046, 'timesteps': 21199} +[2026-04-14 22:43:59] UCB=2.2525 mu=0.6254 sigma=0.8136 params={'n_steer': 9, 'n_throttle': 3, 'learning_rate': 0.0010196345864901517, 'timesteps': 22035} +[2026-04-14 22:43:59] [Champion] 🏆 NEW BEST! Trial 1: mean_reward=50.0000 params={'n_steer': 5} +[2026-04-14 22:43:59] [Champion] 🏆 NEW BEST! Trial 1: mean_reward=80.0000 params={'n_steer': 7} +[2026-04-14 22:43:59] [Champion] 🏆 NEW BEST! Trial 0: mean_reward=50.0000 params={'r': 50} +[2026-04-14 22:43:59] [Champion] 🏆 NEW BEST! Trial 1: mean_reward=80.0000 params={'r': 80} +[2026-04-14 22:43:59] [Champion] 🏆 NEW BEST! Trial 3: mean_reward=90.0000 params={'r': 90} +[2026-04-14 22:43:59] [Champion] 🏆 NEW BEST! Trial 5: mean_reward=75.0000 params={'n_steer': 8} +[2026-04-14 22:43:59] [AutoResearch] Only 1 results — using random proposal. diff --git a/agent/outerloop-results/autoresearch_phase3_log.txt b/agent/outerloop-results/autoresearch_phase3_log.txt index 41ccf64..27e4eb1 100644 --- a/agent/outerloop-results/autoresearch_phase3_log.txt +++ b/agent/outerloop-results/autoresearch_phase3_log.txt @@ -340,3 +340,8 @@ [2026-04-14 22:40:23] [Wave3] Only 0 results — using random proposal. [2026-04-14 22:40:23] [Champion] 🏆 NEW BEST! Trial 3: score=1500.00 (mini_monaco=1500.0) params={'learning_rate': 0.0002, 'steps_per_switch': 8000, 'total_timesteps': 150000} [2026-04-14 22:40:23] [Champion] 🏆 NEW BEST! Trial 1: score=2000.00 (mini_monaco=2000.0) params={} +[2026-04-14 22:44:13] [Wave3] Seed trial 1/2: using hardcoded params. +[2026-04-14 22:44:13] [Wave3] Seed trial 2/2: using hardcoded params. +[2026-04-14 22:44:13] [Wave3] Only 0 results — using random proposal. +[2026-04-14 22:44:13] [Champion] 🏆 NEW BEST! Trial 3: score=1500.00 (mini_monaco=1500.0) params={'learning_rate': 0.0002, 'steps_per_switch': 8000, 'total_timesteps': 150000} +[2026-04-14 22:44:13] [Champion] 🏆 NEW BEST! Trial 1: score=2000.00 (mini_monaco=2000.0) params={} diff --git a/agent/outerloop-results/autoresearch_phase4_log.txt b/agent/outerloop-results/autoresearch_phase4_log.txt new file mode 100644 index 0000000..ab4a670 --- /dev/null +++ b/agent/outerloop-results/autoresearch_phase4_log.txt @@ -0,0 +1,18 @@ +[2026-04-14 22:40:44] ================================================================= +[2026-04-14 22:40:44] [Wave4] Multi-Track Autoresearch — GP+UCB Generalization Search +[2026-04-14 22:40:44] [Wave4] Training tracks : generated_track, mountain_track (no generated_road, no warm-start) +[2026-04-14 22:40:44] [Wave4] Test tracks : mini_monaco only (zero-shot; warren removed — broken done condition) +[2026-04-14 22:40:44] [Wave4] Max trials : 25 | kappa=2.0 | push every 5 +[2026-04-14 22:40:44] [Wave4] Results file : /home/paulh/projects/donkeycar-rl-autoresearch/agent/outerloop-results/autoresearch_results_phase4.jsonl +[2026-04-14 22:40:44] [Wave4] Champion dir : /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-champion +[2026-04-14 22:40:44] [Wave4] Warm start : NONE (training from scratch each trial) +[2026-04-14 22:40:44] ================================================================= +[2026-04-14 22:40:44] [Wave4] Loaded 0 existing Phase 3 results. +[2026-04-14 22:40:44] [Wave4] No Wave 3 champion yet. +[2026-04-14 22:40:44] [Wave4] Starting from trial 1. +[2026-04-14 22:40:44] +[Wave4] ========== Trial 1/25 ========== +[2026-04-14 22:40:44] [Wave4] Seed trial 1/2: using hardcoded params. +[2026-04-14 22:40:44] [Wave4] Proposed params: {'learning_rate': 0.0003, 'steps_per_switch': 6000, 'total_timesteps': 80000} +[2026-04-14 22:40:46] [Wave4] Launching trial 1: {'learning_rate': 0.0003, 'steps_per_switch': 6000, 'total_timesteps': 80000} +[2026-04-14 22:40:46] [Wave4] Command: python3 /home/paulh/projects/donkeycar-rl-autoresearch/agent/multitrack_runner.py --total-timesteps 80000 --steps-per-switch 6000 --learning-rate 0.0003 --eval-episodes 3 --save-dir /home/paulh/projects/donkeycar-rl-autoresearch/agent/models/wave4-trial-0001