{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3389972746372223, "min": 0.3389972746372223, "max": 1.454379916191101, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10077.7109375, "min": 10077.7109375, "max": 44120.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989903.0, "min": 29952.0, "max": 989903.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6189768314361572, "min": -0.10685351490974426, "max": 0.6864830851554871, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 177.02737426757812, "min": -25.777069091796875, "max": 197.70712280273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0025996495969593525, "min": -0.0003400930145289749, "max": 0.13719666004180908, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7434998154640198, "min": -0.09182511270046234, "max": 32.51560974121094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06581924809660349, "min": 0.06524550681241426, "max": 0.0742966294176043, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9872887214490523, "min": 0.49902938685183224, "max": 1.0942741873178758, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016270731601657137, "min": 0.0002794015128843109, "max": 0.01750429619486178, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24406097402485707, "min": 0.0036322196674960414, "max": 0.24554310268528448, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.243589751283999e-05, "min": 1.243589751283999e-05, "max": 0.0004919177159021714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00018653846269259985, "min": 0.00018653846269259985, "max": 0.0058191786361643, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248716000000004, "min": 0.10248716000000004, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373074000000004, "min": 1.3886848, "max": 2.5724803, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584672839999999, "min": 0.0002584672839999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038770092599999984, "min": 0.0038770092599999984, "max": 0.11639718643000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0120148416608572, "min": 0.011760980822145939, "max": 0.5383047461509705, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18022263050079346, "min": 0.1646537333726883, "max": 3.7681331634521484, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.9387755102041, "min": 263.6106194690266, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28610.0, "min": 15984.0, "max": 33496.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6694181660811107, "min": -1.0000000521540642, "max": 1.7063199807703495, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.27239844202995, "min": -29.701401598751545, "max": 192.2109982818365, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6694181660811107, "min": -1.0000000521540642, "max": 1.7063199807703495, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.27239844202995, "min": -29.701401598751545, "max": 192.2109982818365, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03651321022290645, "min": 0.03519283905704461, "max": 11.306585293263197, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6148078120677383, "min": 3.6148078120677383, "max": 180.90536469221115, "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": "1694628646", "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=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": "1694631025" }, "total": 2378.659211449, "count": 1, "self": 0.4889457620001849, "children": { "run_training.setup": { "total": 0.04402335699995774, "count": 1, "self": 0.04402335699995774 }, "TrainerController.start_learning": { "total": 2378.12624233, "count": 1, "self": 1.4353455989958093, "children": { "TrainerController._reset_env": { "total": 4.267457227999955, "count": 1, "self": 4.267457227999955 }, "TrainerController.advance": { "total": 2372.3188606170047, "count": 64099, "self": 1.4675732440150568, "children": { "env_step": { "total": 1703.1907582679914, "count": 64099, "self": 1589.2252049259455, "children": { "SubprocessEnvManager._take_step": { "total": 113.07946581600874, "count": 64099, "self": 5.05829059899304, "children": { "TorchPolicy.evaluate": { "total": 108.0211752170157, "count": 62556, "self": 108.0211752170157 } } }, "workers": { "total": 0.8860875260372154, "count": 64099, "self": 0.0, "children": { "worker_root": { "total": 2372.7385484940355, "count": 64099, "is_parallel": true, "self": 905.4892254560409, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0056753979999939475, "count": 1, "is_parallel": true, "self": 0.004133801000079984, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015415969999139634, "count": 8, "is_parallel": true, "self": 0.0015415969999139634 } } }, "UnityEnvironment.step": { "total": 0.05337520099999438, "count": 1, "is_parallel": true, "self": 0.0005750159999706739, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005537830000434951, "count": 1, "is_parallel": true, "self": 0.0005537830000434951 }, "communicator.exchange": { "total": 0.04932156899997153, "count": 1, "is_parallel": true, "self": 0.04932156899997153 }, "steps_from_proto": { "total": 0.0029248330000086753, "count": 1, "is_parallel": true, "self": 0.00042271200010191023, "children": { "_process_rank_one_or_two_observation": { "total": 0.002502120999906765, "count": 8, "is_parallel": true, "self": 0.002502120999906765 } } } } } } }, "UnityEnvironment.step": { "total": 1467.2493230379946, "count": 64098, "is_parallel": true, "self": 34.93269482407527, "children": { "UnityEnvironment._generate_step_input": { "total": 24.740964786974303, "count": 64098, "is_parallel": true, "self": 24.740964786974303 }, "communicator.exchange": { "total": 1296.0335351729575, "count": 64098, "is_parallel": true, "self": 1296.0335351729575 }, "steps_from_proto": { "total": 111.54212825398758, "count": 64098, "is_parallel": true, "self": 22.617088576873357, "children": { "_process_rank_one_or_two_observation": { "total": 88.92503967711423, "count": 512784, "is_parallel": true, "self": 88.92503967711423 } } } } } } } } } } }, "trainer_advance": { "total": 667.6605291049982, "count": 64099, "self": 2.647343263935227, "children": { "process_trajectory": { "total": 119.39180059805909, "count": 64099, "self": 119.17911446105933, "children": { "RLTrainer._checkpoint": { "total": 0.21268613699976413, "count": 2, "self": 0.21268613699976413 } } }, "_update_policy": { "total": 545.6213852430038, "count": 452, "self": 356.5555417589981, "children": { "TorchPPOOptimizer.update": { "total": 189.0658434840057, "count": 22794, "self": 189.0658434840057 } } } } } } }, "trainer_threads": { "total": 9.129998943535611e-07, "count": 1, "self": 9.129998943535611e-07 }, "TrainerController._save_models": { "total": 0.10457797299977756, "count": 1, "self": 0.0014946529995540914, "children": { "RLTrainer._checkpoint": { "total": 0.10308332000022347, "count": 1, "self": 0.10308332000022347 } } } } } } }