{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15759995579719543, "min": 0.1524069607257843, "max": 1.4654282331466675, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4738.0849609375, "min": 4569.7705078125, "max": 44455.23046875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999944.0, "min": 29952.0, "max": 2999944.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999944.0, "min": 29952.0, "max": 2999944.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7312490940093994, "min": -0.14989693462848663, "max": 0.8460217118263245, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 210.5997314453125, "min": -35.97526550292969, "max": 254.65252685546875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004831002559512854, "min": -0.012503408826887608, "max": 0.27935999631881714, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3913286924362183, "min": -3.5009543895721436, "max": 67.04640197753906, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06646190526745548, "min": 0.0636899242640169, "max": 0.0739444182188305, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9304666737443766, "min": 0.48218907970679525, "max": 1.089773868113601, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016282800757575645, "min": 0.000121838750609823, "max": 0.018800934404102142, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.227959210606059, "min": 0.0015839037579276991, "max": 0.2773260079702595, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5051637840261885e-06, "min": 1.5051637840261885e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1072292976366638e-05, "min": 2.1072292976366638e-05, "max": 0.0039693993768669, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050168809523809, "min": 0.10050168809523809, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070236333333332, "min": 1.3897045333333333, "max": 2.7231331000000005, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.011864071428565e-05, "min": 6.011864071428565e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008416609699999991, "min": 0.0008416609699999991, "max": 0.13232099669, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00550666730850935, "min": 0.005285793449729681, "max": 0.35856184363365173, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07709334045648575, "min": 0.07400111109018326, "max": 2.5099329948425293, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 245.54782608695652, "min": 225.1764705882353, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28238.0, "min": 15984.0, "max": 32554.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6658417237193688, "min": -1.0000000521540642, "max": 1.77334373886697, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 191.5717982277274, "min": -32.000001668930054, "max": 226.98799857497215, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6658417237193688, "min": -1.0000000521540642, "max": 1.77334373886697, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 191.5717982277274, "min": -32.000001668930054, "max": 226.98799857497215, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014478045470415332, "min": 0.01444731566272624, "max": 6.944621751084924, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.664975229097763, "min": 1.6310836759694212, "max": 111.11394801735878, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691615611", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=PyramidsTraining2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1691623823" }, "total": 8212.601290268001, "count": 1, "self": 0.6296181000034267, "children": { "run_training.setup": { "total": 0.06241411099927063, "count": 1, "self": 0.06241411099927063 }, "TrainerController.start_learning": { "total": 8211.909258057, "count": 1, "self": 5.761051371961003, "children": { "TrainerController._reset_env": { "total": 5.376416893000169, "count": 1, "self": 5.376416893000169 }, "TrainerController.advance": { "total": 8200.664617108037, "count": 194070, "self": 5.8719310815813515, "children": { "env_step": { "total": 6099.415543539921, "count": 194070, "self": 5680.379681291129, "children": { "SubprocessEnvManager._take_step": { "total": 415.5696241086471, "count": 194070, "self": 17.17024778769337, "children": { "TorchPolicy.evaluate": { "total": 398.3993763209537, "count": 187562, "self": 398.3993763209537 } } }, "workers": { "total": 3.466238140144924, "count": 194070, "self": 0.0, "children": { "worker_root": { "total": 8190.465136650681, "count": 194070, "is_parallel": true, "self": 2936.7304720924412, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002853761000551458, "count": 1, "is_parallel": true, "self": 0.0008393359994443017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020144250011071563, "count": 8, "is_parallel": true, "self": 0.0020144250011071563 } } }, "UnityEnvironment.step": { "total": 0.051129307000337576, "count": 1, "is_parallel": true, "self": 0.0006189710002217907, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005220619996180176, "count": 1, "is_parallel": true, "self": 0.0005220619996180176 }, "communicator.exchange": { "total": 0.04802532499979861, "count": 1, "is_parallel": true, "self": 0.04802532499979861 }, "steps_from_proto": { "total": 0.0019629490006991546, "count": 1, "is_parallel": true, "self": 0.00037101799989613937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015919310008030152, "count": 8, "is_parallel": true, "self": 0.0015919310008030152 } } } } } } }, "UnityEnvironment.step": { "total": 5253.73466455824, "count": 194069, "is_parallel": true, "self": 116.89475488920925, "children": { "UnityEnvironment._generate_step_input": { "total": 75.56731022933582, "count": 194069, "is_parallel": true, "self": 75.56731022933582 }, "communicator.exchange": { "total": 4700.127839022571, "count": 194069, "is_parallel": true, "self": 4700.127839022571 }, "steps_from_proto": { "total": 361.1447604171244, "count": 194069, "is_parallel": true, "self": 74.73865595261759, "children": { "_process_rank_one_or_two_observation": { "total": 286.4061044645068, "count": 1552552, "is_parallel": true, "self": 286.4061044645068 } } } } } } } } } } }, "trainer_advance": { "total": 2095.3771424865354, "count": 194070, "self": 10.75217776854879, "children": { "process_trajectory": { "total": 368.60414927199326, "count": 194070, "self": 367.88042229899565, "children": { "RLTrainer._checkpoint": { "total": 0.7237269729976106, "count": 6, "self": 0.7237269729976106 } } }, "_update_policy": { "total": 1716.0208154459933, "count": 1382, "self": 1110.647043833963, "children": { "TorchPPOOptimizer.update": { "total": 605.3737716120304, "count": 68364, "self": 605.3737716120304 } } } } } } }, "trainer_threads": { "total": 7.899998308857903e-07, "count": 1, "self": 7.899998308857903e-07 }, "TrainerController._save_models": { "total": 0.10717189400020288, "count": 1, "self": 0.0020474320008361246, "children": { "RLTrainer._checkpoint": { "total": 0.10512446199936676, "count": 1, "self": 0.10512446199936676 } } } } } } }