{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.5577729940414429, "min": 1.5577729940414429, "max": 2.8711555004119873, "count": 24 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8327.8544921875, "min": 7152.794921875, "max": 17492.96484375, "count": 24 }, "SnowballTarget.Step.mean": { "value": 119952.0, "min": 4976.0, "max": 119952.0, "count": 24 }, "SnowballTarget.Step.sum": { "value": 119952.0, "min": 4976.0, "max": 119952.0, "count": 24 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 11.330068588256836, "min": 0.4573516249656677, "max": 11.330068588256836, "count": 24 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 815.7649536132812, "min": 32.929317474365234, "max": 902.7938842773438, "count": 24 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.11255823075771332, "min": 0.10959342122077942, "max": 0.25435778498649597, "count": 24 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 8.104192733764648, "min": 7.890726089477539, "max": 18.31376075744629, "count": 24 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 24 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 6368.0, "min": 4378.0, "max": 6567.0, "count": 24 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0906716643233696, "min": 0.08936119078574505, "max": 0.10692422976172196, "count": 24 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3626866572934784, "min": 0.2680835723572351, "max": 0.41460953043600357, "count": 24 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12022656089237826, "min": 0.05834233026278092, "max": 0.14807391013288293, "count": 24 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.48090624356951306, "min": 0.23336932105112368, "max": 0.5922956405315317, "count": 24 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.146764630000004e-06, "min": 8.146764630000004e-06, "max": 0.00039203555754666665, "count": 24 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.2587058520000015e-05, "min": 3.2587058520000015e-05, "max": 0.00149925335852, "count": 24 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10203666666666666, "min": 0.10203666666666666, "max": 0.1980088888888889, "count": 24 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40814666666666666, "min": 0.31902666666666674, "max": 0.7748133333333332, "count": 24 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00021346300000000008, "min": 0.00021346300000000008, "max": 0.009801088, "count": 24 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0008538520000000003, "min": 0.0008538520000000003, "max": 0.037483852000000005, "count": 24 }, "SnowballTarget.Losses.CuriosityForwardLoss.mean": { "value": 0.049340017580563, "min": 0.049340017580563, "max": 0.11238793617953258, "count": 24 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.197360070322252, "min": 0.15563410755797008, "max": 0.33716380853859773, "count": 24 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 1.4141540664244727, "min": 1.4141540664244727, "max": 2.8354673816503912, "count": 24 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 5.656616265697891, "min": 4.2828076974346505, "max": 10.669374022168101, "count": 24 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.454545454545453, "min": 2.909090909090909, "max": 22.454545454545453, "count": 24 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 494.0, "min": 64.0, "max": 711.0, "count": 24 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.454545454545453, "min": 2.909090909090909, "max": 22.454545454545453, "count": 24 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 494.0, "min": 64.0, "max": 711.0, "count": 24 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.20842078646687281, "min": 0.20536660502495413, "max": 0.302854514691386, "count": 24 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 4.585257302271202, "min": 4.518065310548991, "max": 7.958207841962576, "count": 24 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 24 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 24 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739206661", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739207027" }, "total": 366.6684852830001, "count": 1, "self": 0.43187780299990663, "children": { "run_training.setup": { "total": 0.029345969000132754, "count": 1, "self": 0.029345969000132754 }, "TrainerController.start_learning": { "total": 366.20726151100007, "count": 1, "self": 0.6093387509949935, "children": { "TrainerController._reset_env": { "total": 2.414866170999858, "count": 1, "self": 2.414866170999858 }, "TrainerController.advance": { "total": 363.0920417230052, "count": 11005, "self": 0.2074296979983501, "children": { "env_step": { "total": 362.88461202500685, "count": 11005, "self": 284.4297636560018, "children": { "SubprocessEnvManager._take_step": { "total": 78.26171221600043, "count": 11005, "self": 0.991260860004104, "children": { "TorchPolicy.evaluate": { "total": 77.27045135599633, "count": 11005, "self": 77.27045135599633 } } }, "workers": { "total": 0.19313615300461606, "count": 11005, "self": 0.0, "children": { "worker_root": { "total": 365.18384611800525, "count": 11005, "is_parallel": true, "self": 220.45321479002064, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028145039998435095, "count": 1, "is_parallel": true, "self": 0.0007361789998867607, "children": { "_process_rank_one_or_two_observation": { "total": 0.002078324999956749, "count": 10, "is_parallel": true, "self": 0.002078324999956749 } } }, "UnityEnvironment.step": { "total": 0.06449263800004701, "count": 1, "is_parallel": true, "self": 0.0005959709999387997, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003966610001953086, "count": 1, "is_parallel": true, "self": 0.0003966610001953086 }, "communicator.exchange": { "total": 0.06152797400000054, "count": 1, "is_parallel": true, "self": 0.06152797400000054 }, "steps_from_proto": { "total": 0.0019720319999123603, "count": 1, "is_parallel": true, "self": 0.00038622000010946067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015858119998028997, "count": 10, "is_parallel": true, "self": 0.0015858119998028997 } } } } } } }, "UnityEnvironment.step": { "total": 144.7306313279846, "count": 11004, "is_parallel": true, "self": 6.164258635984197, "children": { "UnityEnvironment._generate_step_input": { "total": 3.3917431570159806, "count": 11004, "is_parallel": true, "self": 3.3917431570159806 }, "communicator.exchange": { "total": 114.39247847900333, "count": 11004, "is_parallel": true, "self": 114.39247847900333 }, "steps_from_proto": { "total": 20.782151055981103, "count": 11004, "is_parallel": true, "self": 4.146583734015621, "children": { "_process_rank_one_or_two_observation": { "total": 16.635567321965482, "count": 110040, "is_parallel": true, "self": 16.635567321965482 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.001371276000099897, "count": 1, "self": 0.001371276000099897, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 363.6459302829876, "count": 6012, "is_parallel": true, "self": 0.1291725459764166, "children": { "process_trajectory": { "total": 56.10390000901111, "count": 6012, "is_parallel": true, "self": 54.67397870901141, "children": { "RLTrainer._checkpoint": { "total": 1.4299212999997053, "count": 8, "is_parallel": true, "self": 1.4299212999997053 } } }, "_update_policy": { "total": 307.41285772800006, "count": 82, "is_parallel": true, "self": 152.3872712640043, "children": { "TorchPPOOptimizer.update": { "total": 155.02558646399575, "count": 7300, "is_parallel": true, "self": 155.02558646399575 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08964358999992328, "count": 1, "self": 0.000892784999905416, "children": { "RLTrainer._checkpoint": { "total": 0.08875080500001786, "count": 1, "self": 0.08875080500001786 } } } } } } }