From cb82121e98b6ad38557ea2e07a23f8a478979cac Mon Sep 17 00:00:00 2001 From: Paul Huliganga Date: Mon, 13 Apr 2026 19:18:00 -0400 Subject: [PATCH] autoresearch: phase1 trial 50 results Agent: pi Tests: N/A Tests-Added: 0 TypeScript: N/A --- agent/outerloop-results/autoresearch_phase1_log.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/agent/outerloop-results/autoresearch_phase1_log.txt b/agent/outerloop-results/autoresearch_phase1_log.txt index 7ab84e0..5bde57a 100644 --- a/agent/outerloop-results/autoresearch_phase1_log.txt +++ b/agent/outerloop-results/autoresearch_phase1_log.txt @@ -1980,3 +1980,14 @@ [2026-04-13 19:17:56] mean_reward=3332.0024 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.0010146909128518657, 'timesteps': 4979, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} [2026-04-13 19:17:56] mean_reward=2306.7610 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0004488352572615814, 'timesteps': 4898, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} [2026-04-13 19:17:56] mean_reward=2286.9085 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0003386484278685721, 'timesteps': 4977, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} +[2026-04-13 19:17:58] [AutoResearch] Git push complete after trial 50 +[2026-04-13 19:18:00] [AutoResearch] All trials complete! +[2026-04-13 19:18:00] [AutoResearch] === Trial 50 Summary === +[2026-04-13 19:18:00] Total Phase 1 runs: 82 +[2026-04-13 19:18:00] Champion: trial=5 mean_reward=4582.7984 params={'n_steer': 7, 'n_throttle': 3, 'learning_rate': 0.0006801262090358742, 'timesteps': 4787, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} +[2026-04-13 19:18:00] Top 5: +[2026-04-13 19:18:00] mean_reward=4462.2930 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.0004222996001111442, 'timesteps': 4942, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} +[2026-04-13 19:18:00] mean_reward=4314.8893 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0007707060431765714, 'timesteps': 4976, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} +[2026-04-13 19:18:00] mean_reward=3332.0024 params={'n_steer': 4, 'n_throttle': 3, 'learning_rate': 0.0010146909128518657, 'timesteps': 4979, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} +[2026-04-13 19:18:00] mean_reward=2306.7610 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0004488352572615814, 'timesteps': 4898, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True} +[2026-04-13 19:18:00] mean_reward=2286.9085 params={'n_steer': 5, 'n_throttle': 3, 'learning_rate': 0.0003386484278685721, 'timesteps': 4977, 'agent': 'ppo', 'eval_episodes': 3, 'reward_shaping': True}