{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9455969333648682, "min": 0.9455969333648682, "max": 1.4872900247573853, "count": 6 }, "Pyramids.Policy.Entropy.sum": { "value": 28322.51953125, "min": 28322.51953125, "max": 45118.4296875, "count": 6 }, "Pyramids.Step.mean": { "value": 89885.0, "min": 29952.0, "max": 89885.0, "count": 6 }, "Pyramids.Step.sum": { "value": 89885.0, "min": 29952.0, "max": 89885.0, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05936215817928314, "min": -0.08292374759912491, "max": -0.05936215817928314, "count": 6 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -14.246917724609375, "min": -19.984622955322266, "max": -14.246917724609375, "count": 6 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.14061778783798218, "min": 0.07758460193872452, "max": 0.18618783354759216, "count": 6 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 33.748268127441406, "min": 18.387550354003906, "max": 44.87126922607422, "count": 6 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07206202754827666, "min": 0.07014854968305184, "max": 0.07206202754827666, "count": 6 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7206202754827666, "min": 0.5011703064676907, "max": 0.7206202754827666, "count": 6 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001100028615166773, "min": 0.001100028615166773, "max": 0.004225976141820382, "count": 6 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.01100028615166773, "min": 0.01100028615166773, "max": 0.02958183299274267, "count": 6 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.562557479149998e-05, "min": 7.562557479149998e-05, "max": 0.0002515063018788571, "count": 6 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0007562557479149998, "min": 0.0007562557479149998, "max": 0.0017605441131519997, "count": 6 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1252085, "min": 0.1252085, "max": 0.1838354285714286, "count": 6 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.2520850000000001, "min": 1.232842, "max": 1.2868480000000002, "count": 6 }, "Pyramids.Policy.Beta.mean": { "value": 0.0025283291500000004, "min": 0.0025283291500000004, "max": 0.008385159314285713, "count": 6 }, "Pyramids.Policy.Beta.sum": { "value": 0.025283291500000003, "min": 0.025283291500000003, "max": 0.058696115199999996, "count": 6 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.10891442000865936, "min": 0.10891442000865936, "max": 0.3628199100494385, "count": 6 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.089144229888916, "min": 1.089144229888916, "max": 2.5397393703460693, "count": 6 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 970.21875, "min": 970.21875, "max": 999.0, "count": 6 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31047.0, "min": 15984.0, "max": 32661.0, "count": 6 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9086438023950905, "min": -1.0000000521540642, "max": -0.9086438023950905, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.076601676642895, "min": -30.69300167262554, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9086438023950905, "min": -1.0000000521540642, "max": -0.9086438023950905, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.076601676642895, "min": -30.69300167262554, "max": -16.000000834465027, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 1.2167230206541717, "min": 1.2167230206541717, "max": 7.217564575374126, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 38.935136660933495, "min": 38.935136660933495, "max": 115.48103320598602, "count": 6 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678308526", "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=Pyramids3 --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678308837" }, "total": 310.473550533, "count": 1, "self": 0.6272936769996704, "children": { "run_training.setup": { "total": 0.22715203000007023, "count": 1, "self": 0.22715203000007023 }, "TrainerController.start_learning": { "total": 309.61910482600024, "count": 1, "self": 0.23349607298177943, "children": { "TrainerController._reset_env": { "total": 4.2025894809999045, "count": 1, "self": 4.2025894809999045 }, "TrainerController.advance": { "total": 305.078291765019, "count": 6318, "self": 0.254343655028606, "children": { "env_step": { "total": 188.29488731502852, "count": 6318, "self": 172.0069744799739, "children": { "SubprocessEnvManager._take_step": { "total": 16.136239786021633, "count": 6318, "self": 1.1266490970460836, "children": { "TorchPolicy.evaluate": { "total": 15.00959068897555, "count": 6311, "self": 15.00959068897555 } } }, "workers": { "total": 0.15167304903297918, "count": 6318, "self": 0.0, "children": { "worker_root": { "total": 309.1441771630066, "count": 6318, "is_parallel": true, "self": 154.1350652050055, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030792709999332146, "count": 1, "is_parallel": true, "self": 0.0008337269996445684, "children": { "_process_rank_one_or_two_observation": { "total": 0.002245544000288646, "count": 8, "is_parallel": true, "self": 0.002245544000288646 } } }, "UnityEnvironment.step": { "total": 0.06693998999980977, "count": 1, "is_parallel": true, "self": 0.000668037999275839, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005614480000986077, "count": 1, "is_parallel": true, "self": 0.0005614480000986077 }, "communicator.exchange": { "total": 0.0637082560001545, "count": 1, "is_parallel": true, "self": 0.0637082560001545 }, "steps_from_proto": { "total": 0.002002248000280815, "count": 1, "is_parallel": true, "self": 0.0004273570002624183, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015748910000183969, "count": 8, "is_parallel": true, "self": 0.0015748910000183969 } } } } } } }, "UnityEnvironment.step": { "total": 155.00911195800109, "count": 6317, "is_parallel": true, "self": 4.340061899964439, "children": { "UnityEnvironment._generate_step_input": { "total": 2.6101236940330637, "count": 6317, "is_parallel": true, "self": 2.6101236940330637 }, "communicator.exchange": { "total": 135.24427694400947, "count": 6317, "is_parallel": true, "self": 135.24427694400947 }, "steps_from_proto": { "total": 12.814649419994112, "count": 6317, "is_parallel": true, "self": 2.9236324470330146, "children": { "_process_rank_one_or_two_observation": { "total": 9.891016972961097, "count": 50536, "is_parallel": true, "self": 9.891016972961097 } } } } } } } } } } }, "trainer_advance": { "total": 116.52906079496188, "count": 6318, "self": 0.3254541569722278, "children": { "process_trajectory": { "total": 16.0190112249893, "count": 6318, "self": 16.0190112249893 }, "_update_policy": { "total": 100.18459541300035, "count": 30, "self": 43.28591911199828, "children": { "TorchPPOOptimizer.update": { "total": 56.89867630100207, "count": 2331, "self": 56.89867630100207 } } } } } } }, "trainer_threads": { "total": 1.647999852139037e-06, "count": 1, "self": 1.647999852139037e-06 }, "TrainerController._save_models": { "total": 0.1047258589997, "count": 1, "self": 0.0020763009997608606, "children": { "RLTrainer._checkpoint": { "total": 0.10264955799993913, "count": 1, "self": 0.10264955799993913 } } } } } } }