{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30728045105934143, "min": 0.2893276810646057, "max": 1.4328333139419556, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9228.24609375, "min": 8665.9423828125, "max": 43466.4296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5620554089546204, "min": -0.10714234411716461, "max": 0.6600363254547119, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 155.68934631347656, "min": -25.928447723388672, "max": 187.00778198242188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015303066000342369, "min": -0.017249807715415955, "max": 0.4968908727169037, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.238949298858643, "min": -4.553949356079102, "max": 117.76313781738281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07020235056012246, "min": 0.06429006855062395, "max": 0.0741048734660546, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9828329078417144, "min": 0.48413890474807103, "max": 1.0672789177470432, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01709228551959461, "min": 0.0017080195988866407, "max": 0.01709228551959461, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2392919972743245, "min": 0.018788215587753048, "max": 0.2392919972743245, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5221474926499956e-06, "min": 7.5221474926499956e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010531006489709993, "min": 0.00010531006489709993, "max": 0.003634422188526, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250735000000001, "min": 0.10250735000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351029000000002, "min": 1.3886848, "max": 2.6114740000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026048426499999987, "min": 0.00026048426499999987, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003646779709999998, "min": 0.003646779709999998, "max": 0.1211662526, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012594103813171387, "min": 0.012594103813171387, "max": 0.5793039202690125, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17631745338439941, "min": 0.17631745338439941, "max": 4.0551276206970215, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 328.6304347826087, "min": 266.9626168224299, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30234.0, "min": 15984.0, "max": 32717.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5409043316283952, "min": -1.0000000521540642, "max": 1.7359622496197809, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.76319850981236, "min": -30.749001666903496, "max": 184.01199845969677, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5409043316283952, "min": -1.0000000521540642, "max": 1.7359622496197809, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.76319850981236, "min": -30.749001666903496, "max": 184.01199845969677, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042480772825397056, "min": 0.04056512791471762, "max": 12.810467923991382, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.908231099936529, "min": 3.908231099936529, "max": 204.9674867838621, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682506611", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "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": "1682508983" }, "total": 2372.0786936759996, "count": 1, "self": 0.9474366879999252, "children": { "run_training.setup": { "total": 0.18940137900017362, "count": 1, "self": 0.18940137900017362 }, "TrainerController.start_learning": { "total": 2370.9418556089995, "count": 1, "self": 1.3674607919688242, "children": { "TrainerController._reset_env": { "total": 5.447751674000074, "count": 1, "self": 5.447751674000074 }, "TrainerController.advance": { "total": 2363.983103386031, "count": 64092, "self": 1.5493081120257557, "children": { "env_step": { "total": 1722.059667493068, "count": 64092, "self": 1613.552520740029, "children": { "SubprocessEnvManager._take_step": { "total": 107.65694239802451, "count": 64092, "self": 5.002022713001907, "children": { "TorchPolicy.evaluate": { "total": 102.6549196850226, "count": 62564, "self": 102.6549196850226 } } }, "workers": { "total": 0.8502043550145117, "count": 64092, "self": 0.0, "children": { "worker_root": { "total": 2365.133253711004, "count": 64092, "is_parallel": true, "self": 868.3256828780745, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008585430000039196, "count": 1, "is_parallel": true, "self": 0.005189249000295604, "children": { "_process_rank_one_or_two_observation": { "total": 0.003396180999743592, "count": 8, "is_parallel": true, "self": 0.003396180999743592 } } }, "UnityEnvironment.step": { "total": 0.04640061899999637, "count": 1, "is_parallel": true, "self": 0.0005726060003325983, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004835369998090755, "count": 1, "is_parallel": true, "self": 0.0004835369998090755 }, "communicator.exchange": { "total": 0.04374360099996011, "count": 1, "is_parallel": true, "self": 0.04374360099996011 }, "steps_from_proto": { "total": 0.001600874999894586, "count": 1, "is_parallel": true, "self": 0.00038386199980777747, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012170130000868085, "count": 8, "is_parallel": true, "self": 0.0012170130000868085 } } } } } } }, "UnityEnvironment.step": { "total": 1496.8075708329293, "count": 64091, "is_parallel": true, "self": 33.725272949031705, "children": { "UnityEnvironment._generate_step_input": { "total": 23.01736954893704, "count": 64091, "is_parallel": true, "self": 23.01736954893704 }, "communicator.exchange": { "total": 1343.8366461170158, "count": 64091, "is_parallel": true, "self": 1343.8366461170158 }, "steps_from_proto": { "total": 96.22828221794475, "count": 64091, "is_parallel": true, "self": 20.376292947941465, "children": { "_process_rank_one_or_two_observation": { "total": 75.85198927000329, "count": 512728, "is_parallel": true, "self": 75.85198927000329 } } } } } } } } } } }, "trainer_advance": { "total": 640.374127780937, "count": 64092, "self": 2.6256474379235897, "children": { "process_trajectory": { "total": 111.05944789301657, "count": 64092, "self": 110.74155738501668, "children": { "RLTrainer._checkpoint": { "total": 0.31789050799989127, "count": 2, "self": 0.31789050799989127 } } }, "_update_policy": { "total": 526.6890324499968, "count": 453, "self": 338.78362756698016, "children": { "TorchPPOOptimizer.update": { "total": 187.90540488301667, "count": 22794, "self": 187.90540488301667 } } } } } } }, "trainer_threads": { "total": 1.3300000318849925e-06, "count": 1, "self": 1.3300000318849925e-06 }, "TrainerController._save_models": { "total": 0.14353842699983943, "count": 1, "self": 0.0021694199995181407, "children": { "RLTrainer._checkpoint": { "total": 0.1413690070003213, "count": 1, "self": 0.1413690070003213 } } } } } } }