{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.222472906112671, "min": 2.150395631790161, "max": 3.2957444190979004, "count": 410 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45445.125, "min": 11898.0341796875, "max": 119979.5, "count": 410 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.40952380952381, "min": 36.644444444444446, "max": 999.0, "count": 410 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19492.0, "min": 13872.0, "max": 26748.0, "count": 410 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1495.1556634113836, "min": 1182.8381900155546, "max": 1524.1577783143723, "count": 390 }, "SoccerTwos.Self-play.ELO.sum": { "value": 313982.68931639055, "min": 2365.8449519133424, "max": 398427.4066052799, "count": 390 }, "SoccerTwos.Step.mean": { "value": 4099994.0, "min": 9392.0, "max": 4099994.0, "count": 410 }, "SoccerTwos.Step.sum": { "value": 4099994.0, "min": 9392.0, "max": 4099994.0, "count": 410 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.08788485080003738, "min": -0.1031632274389267, "max": 0.17467674612998962, "count": 410 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -18.45581817626953, "min": -19.26350975036621, "max": 28.022117614746094, "count": 410 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.08951694518327713, "min": -0.09875043481588364, "max": 0.18148963153362274, "count": 410 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -18.798559188842773, "min": -20.47150421142578, "max": 28.274028778076172, "count": 410 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 410 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 410 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1491219026701791, "min": -0.5323999961217244, "max": 0.5446758599116884, "count": 410 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -31.31559956073761, "min": -54.088399827480316, "max": 50.11659961938858, "count": 410 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1491219026701791, "min": -0.5323999961217244, "max": 0.5446758599116884, "count": 410 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -31.31559956073761, "min": -54.088399827480316, "max": 50.11659961938858, "count": 410 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 410 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 410 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01561849357385654, "min": 0.010795206901578543, "max": 0.02451171148568392, "count": 196 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01561849357385654, "min": 0.010795206901578543, "max": 0.02451171148568392, "count": 196 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10136733800172806, "min": 1.674589735027136e-06, "max": 0.11446920037269592, "count": 196 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10136733800172806, "min": 1.674589735027136e-06, "max": 0.11446920037269592, "count": 196 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10472086866696675, "min": 1.924790747883283e-06, "max": 0.11718133638302485, "count": 196 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10472086866696675, "min": 1.924790747883283e-06, "max": 0.11718133638302485, "count": 196 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 196 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 196 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 196 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 196 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 196 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 196 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713695258", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/Users/baptistepugnaire/miniconda3/envs/mlagents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1713708891" }, "total": 13633.117216667, "count": 1, "self": 0.2868944169895258, "children": { "run_training.setup": { "total": 0.016692958000930957, "count": 1, "self": 0.016692958000930957 }, "TrainerController.start_learning": { "total": 13632.81362929201, "count": 1, "self": 2.94447523423878, "children": { "TrainerController._reset_env": { "total": 4.608890749062994, "count": 21, "self": 4.608890749062994 }, "TrainerController.advance": { "total": 13625.139905475691, "count": 278026, "self": 2.6332931292854482, "children": { "env_step": { "total": 10638.947252990401, "count": 278026, "self": 10196.129751014683, "children": { "SubprocessEnvManager._take_step": { "total": 440.71255384848337, "count": 278026, "self": 12.537217989942292, "children": { "TorchPolicy.evaluate": { "total": 428.1753358585411, "count": 519994, "self": 428.1753358585411 } } }, "workers": { "total": 2.1049481272348203, "count": 278025, "self": 0.0, "children": { "worker_root": { "total": 13624.222950715848, "count": 278025, "is_parallel": true, "self": 3784.5390433195425, "children": { "steps_from_proto": { "total": 0.030222702989703976, "count": 42, "is_parallel": true, "self": 0.00413294903410133, "children": { "_process_rank_one_or_two_observation": { "total": 0.026089753955602646, "count": 168, "is_parallel": true, "self": 0.026089753955602646 } } }, "UnityEnvironment.step": { "total": 9839.653684693316, "count": 278025, "is_parallel": true, "self": 29.247054673047387, "children": { "UnityEnvironment._generate_step_input": { "total": 179.0981082314538, "count": 278025, "is_parallel": true, "self": 179.0981082314538 }, "communicator.exchange": { "total": 9281.794215923248, "count": 278025, "is_parallel": true, "self": 9281.794215923248 }, "steps_from_proto": { "total": 349.5143058655667, "count": 556050, "is_parallel": true, "self": 43.40122344321571, "children": { "_process_rank_one_or_two_observation": { "total": 306.113082422351, "count": 2224200, "is_parallel": true, "self": 306.113082422351 } } } } } } } } } } }, "trainer_advance": { "total": 2983.5593593560043, "count": 278025, "self": 34.51993830889114, "children": { "process_trajectory": { "total": 540.1099216259026, "count": 278025, "self": 538.5574000409397, "children": { "RLTrainer._checkpoint": { "total": 1.5525215849629603, "count": 8, "self": 1.5525215849629603 } } }, "_update_policy": { "total": 2408.9294994212105, "count": 196, "self": 237.72295395177207, "children": { "TorchPOCAOptimizer.update": { "total": 2171.2065454694384, "count": 5889, "self": 2171.2065454694384 } } } } } } }, "trainer_threads": { "total": 4.169996827840805e-07, "count": 1, "self": 4.169996827840805e-07 }, "TrainerController._save_models": { "total": 0.12035741601721384, "count": 1, "self": 0.008130874019116163, "children": { "RLTrainer._checkpoint": { "total": 0.11222654199809767, "count": 1, "self": 0.11222654199809767 } } } } } } }