{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.312359094619751, "min": 0.3076399564743042, "max": 1.4103870391845703, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9355.779296875, "min": 9151.884765625, "max": 42785.5, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5847235321998596, "min": -0.14529451727867126, "max": 0.6554327011108398, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.38369750976562, "min": -34.43479919433594, "max": 182.86572265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.02807162143290043, "min": -0.02807162143290043, "max": 0.3776421546936035, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -7.747767448425293, "min": -7.747767448425293, "max": 89.50119018554688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06735456386134804, "min": 0.06499023197878463, "max": 0.07260351228221687, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9429638940588725, "min": 0.5081308259747136, "max": 1.084513437661443, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015652973032307015, "min": 0.0009207465044709017, "max": 0.015783666534763242, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2191416224522982, "min": 0.011048958053650821, "max": 0.23675499802144861, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.308054706871433e-06, "min": 7.308054706871433e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010231276589620006, "min": 0.00010231276589620006, "max": 0.0035101667299444993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243598571428572, "min": 0.10243598571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341038000000002, "min": 1.3886848, "max": 2.5700555, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025335497285714306, "min": 0.00025335497285714306, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003546969620000003, "min": 0.003546969620000003, "max": 0.11702854445, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014090928249061108, "min": 0.013619811274111271, "max": 0.4901733696460724, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19727300107479095, "min": 0.19727300107479095, "max": 3.431213617324829, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 334.1304347826087, "min": 296.7551020408163, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30740.0, "min": 15984.0, "max": 34759.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6429977814902317, "min": -1.0000000521540642, "max": 1.6711608116159733, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.51279811561108, "min": -30.571601636707783, "max": 162.91659806668758, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6429977814902317, "min": -1.0000000521540642, "max": 1.6711608116159733, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.51279811561108, "min": -30.571601636707783, "max": 162.91659806668758, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04798116156598553, "min": 0.04212589473231952, "max": 9.666238343343139, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.366285702504683, "min": 4.128337683767313, "max": 154.65981349349022, "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": "1677955155", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677957415" }, "total": 2260.2522484300007, "count": 1, "self": 0.6597295740011759, "children": { "run_training.setup": { "total": 0.11078627299957589, "count": 1, "self": 0.11078627299957589 }, "TrainerController.start_learning": { "total": 2259.481732583, "count": 1, "self": 1.3405574429561966, "children": { "TrainerController._reset_env": { "total": 6.035625127999992, "count": 1, "self": 6.035625127999992 }, "TrainerController.advance": { "total": 2252.0112835490436, "count": 64001, "self": 1.3642974970434807, "children": { "env_step": { "total": 1525.3255810859855, "count": 64001, "self": 1416.4180292928932, "children": { "SubprocessEnvManager._take_step": { "total": 108.11524997618744, "count": 64001, "self": 4.578147036352675, "children": { "TorchPolicy.evaluate": { "total": 103.53710293983477, "count": 62555, "self": 35.40323402802642, "children": { "TorchPolicy.sample_actions": { "total": 68.13386891180835, "count": 62555, "self": 68.13386891180835 } } } } }, "workers": { "total": 0.7923018169049101, "count": 64001, "self": 0.0, "children": { "worker_root": { "total": 2254.8949098070407, "count": 64001, "is_parallel": true, "self": 949.5855280807491, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001997071000005235, "count": 1, "is_parallel": true, "self": 0.0006976089998715906, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012994620001336443, "count": 8, "is_parallel": true, "self": 0.0012994620001336443 } } }, "UnityEnvironment.step": { "total": 0.0450351130002673, "count": 1, "is_parallel": true, "self": 0.0004998100012016948, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004357609996077372, "count": 1, "is_parallel": true, "self": 0.0004357609996077372 }, "communicator.exchange": { "total": 0.042546124999716994, "count": 1, "is_parallel": true, "self": 0.042546124999716994 }, "steps_from_proto": { "total": 0.0015534169997408753, "count": 1, "is_parallel": true, "self": 0.00040478900154994335, "children": { "_process_rank_one_or_two_observation": { "total": 0.001148627998190932, "count": 8, "is_parallel": true, "self": 0.001148627998190932 } } } } } } }, "UnityEnvironment.step": { "total": 1305.3093817262916, "count": 64000, "is_parallel": true, "self": 30.47806334417055, "children": { "UnityEnvironment._generate_step_input": { "total": 22.245464026982518, "count": 64000, "is_parallel": true, "self": 22.245464026982518 }, "communicator.exchange": { "total": 1163.5787640421095, "count": 64000, "is_parallel": true, "self": 1163.5787640421095 }, "steps_from_proto": { "total": 89.00709031302904, "count": 64000, "is_parallel": true, "self": 21.044585022043975, "children": { "_process_rank_one_or_two_observation": { "total": 67.96250529098506, "count": 512000, "is_parallel": true, "self": 67.96250529098506 } } } } } } } } } } }, "trainer_advance": { "total": 725.3214049660146, "count": 64001, "self": 2.4746005599463388, "children": { "process_trajectory": { "total": 160.10395018006784, "count": 64001, "self": 159.91586251406807, "children": { "RLTrainer._checkpoint": { "total": 0.1880876659997739, "count": 2, "self": 0.1880876659997739 } } }, "_update_policy": { "total": 562.7428542260004, "count": 455, "self": 221.19335779999255, "children": { "TorchPPOOptimizer.update": { "total": 341.54949642600786, "count": 22803, "self": 341.54949642600786 } } } } } } }, "trainer_threads": { "total": 9.830000635702163e-07, "count": 1, "self": 9.830000635702163e-07 }, "TrainerController._save_models": { "total": 0.09426548000010371, "count": 1, "self": 0.001551786999698379, "children": { "RLTrainer._checkpoint": { "total": 0.09271369300040533, "count": 1, "self": 0.09271369300040533 } } } } } } }