{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3013733923435211, "min": 0.3013733923435211, "max": 1.3869065046310425, "count": 51 }, "Pyramids.Policy.Entropy.sum": { "value": 8944.7626953125, "min": 8944.7626953125, "max": 42073.1953125, "count": 51 }, "Pyramids.Step.mean": { "value": 1529874.0, "min": 29952.0, "max": 1529874.0, "count": 51 }, "Pyramids.Step.sum": { "value": 1529874.0, "min": 29952.0, "max": 1529874.0, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6376602053642273, "min": -0.10865096747875214, "max": 0.8013395071029663, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.82017517089844, "min": -26.07623291015625, "max": 226.77908325195312, "count": 51 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0068503571674227715, "min": -0.023107096552848816, "max": 0.5127955675125122, "count": 51 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9318007230758667, "min": -6.192701816558838, "max": 121.53254699707031, "count": 51 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06443422263677635, "min": 0.06260647159970609, "max": 0.07329989886139611, "count": 51 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9020791169148689, "min": 0.5068109285935423, "max": 1.0994984829209415, "count": 51 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015139336185770323, "min": 0.00015302859993752047, "max": 0.016004248205544653, "count": 51 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21195070660078452, "min": 0.0021424003991252867, "max": 0.22433037275842774, "count": 51 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014858180761560474, "min": 0.00014858180761560474, "max": 0.00029838354339596195, "count": 51 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020801453066184666, "min": 0.0020801453066184666, "max": 0.004011339262886934, "count": 51 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14952725238095238, "min": 0.14952725238095238, "max": 0.19946118095238097, "count": 51 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0933815333333334, "min": 1.3962282666666668, "max": 2.737113066666667, "count": 51 }, "Pyramids.Policy.Beta.mean": { "value": 0.004957772512857143, "min": 0.004957772512857143, "max": 0.009946171977142856, "count": 51 }, "Pyramids.Policy.Beta.sum": { "value": 0.06940881518, "min": 0.06940881518, "max": 0.13371759536, "count": 51 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009086927399039268, "min": 0.008219473995268345, "max": 0.6906247138977051, "count": 51 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12721697986125946, "min": 0.11507263034582138, "max": 4.8343729972839355, "count": 51 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.90291262135923, "min": 256.1304347826087, "max": 999.0, "count": 51 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30581.0, "min": 15984.0, "max": 33657.0, "count": 51 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6642504691788294, "min": -1.0000000521540642, "max": 1.743869549813478, "count": 51 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.41779832541943, "min": -30.478001676499844, "max": 200.54499822854996, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6642504691788294, "min": -1.0000000521540642, "max": 1.743869549813478, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.41779832541943, "min": -30.478001676499844, "max": 200.54499822854996, "count": 51 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028028628551536827, "min": 0.025254321085201516, "max": 13.771021699532866, "count": 51 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8869487408082932, "min": 2.50017778743495, "max": 220.33634719252586, "count": 51 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710938354", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710941734" }, "total": 3379.7989960259997, "count": 1, "self": 0.8631011649995344, "children": { "run_training.setup": { "total": 0.07804342800000086, "count": 1, "self": 0.07804342800000086 }, "TrainerController.start_learning": { "total": 3378.857851433, "count": 1, "self": 2.056766178111502, "children": { "TrainerController._reset_env": { "total": 2.413214691000121, "count": 1, "self": 2.413214691000121 }, "TrainerController.advance": { "total": 3374.2018100228884, "count": 98993, "self": 2.096173182968869, "children": { "env_step": { "total": 2411.2447738710625, "count": 98993, "self": 2216.142988056031, "children": { "SubprocessEnvManager._take_step": { "total": 193.85823684998104, "count": 98993, "self": 6.975426753015199, "children": { "TorchPolicy.evaluate": { "total": 186.88281009696584, "count": 96693, "self": 186.88281009696584 } } }, "workers": { "total": 1.2435489650506497, "count": 98992, "self": 0.0, "children": { "worker_root": { "total": 3371.215016163822, "count": 98992, "is_parallel": true, "self": 1335.4780909909382, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00206476500034114, "count": 1, "is_parallel": true, "self": 0.000567830000363756, "children": { "_process_rank_one_or_two_observation": { "total": 0.001496934999977384, "count": 8, "is_parallel": true, "self": 0.001496934999977384 } } }, "UnityEnvironment.step": { "total": 0.058058949999576726, "count": 1, "is_parallel": true, "self": 0.006277705999764294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005153219999556313, "count": 1, "is_parallel": true, "self": 0.0005153219999556313 }, "communicator.exchange": { "total": 0.0457263220000641, "count": 1, "is_parallel": true, "self": 0.0457263220000641 }, "steps_from_proto": { "total": 0.005539599999792699, "count": 1, "is_parallel": true, "self": 0.004155742999955692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013838569998370076, "count": 8, "is_parallel": true, "self": 0.0013838569998370076 } } } } } } }, "UnityEnvironment.step": { "total": 2035.7369251728837, "count": 98991, "is_parallel": true, "self": 52.44228848695866, "children": { "UnityEnvironment._generate_step_input": { "total": 35.41980783892086, "count": 98991, "is_parallel": true, "self": 35.41980783892086 }, "communicator.exchange": { "total": 1797.474503363885, "count": 98991, "is_parallel": true, "self": 1797.474503363885 }, "steps_from_proto": { "total": 150.4003254831191, "count": 98991, "is_parallel": true, "self": 30.369625673021346, "children": { "_process_rank_one_or_two_observation": { "total": 120.03069981009776, "count": 791928, "is_parallel": true, "self": 120.03069981009776 } } } } } } } } } } }, "trainer_advance": { "total": 960.860862968857, "count": 98992, "self": 4.231509163881583, "children": { "process_trajectory": { "total": 196.40715311397207, "count": 98992, "self": 196.08417555897267, "children": { "RLTrainer._checkpoint": { "total": 0.3229775549993974, "count": 3, "self": 0.3229775549993974 } } }, "_update_policy": { "total": 760.2222006910033, "count": 710, "self": 442.7136882519826, "children": { "TorchPPOOptimizer.update": { "total": 317.5085124390207, "count": 35217, "self": 317.5085124390207 } } } } } } }, "trainer_threads": { "total": 1.2620002962648869e-06, "count": 1, "self": 1.2620002962648869e-06 }, "TrainerController._save_models": { "total": 0.18605927899989183, "count": 1, "self": 0.0021195889994487516, "children": { "RLTrainer._checkpoint": { "total": 0.18393969000044308, "count": 1, "self": 0.18393969000044308 } } } } } } }