{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0700390338897705, "min": 1.0700390338897705, "max": 1.4682573080062866, "count": 2 }, "Pyramids.Policy.Entropy.sum": { "value": 32049.80859375, "min": 32049.80859375, "max": 44541.0546875, "count": 2 }, "Pyramids.Step.mean": { "value": 59888.0, "min": 29952.0, "max": 59888.0, "count": 2 }, "Pyramids.Step.sum": { "value": 59888.0, "min": 29952.0, "max": 59888.0, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03291097283363342, "min": -0.03291097283363342, "max": 0.10380222648382187, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -7.931544780731201, "min": -7.931544780731201, "max": 24.60112762451172, "count": 2 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.49802446365356445, "min": 0.3091415464878082, "max": 0.49802446365356445, "count": 2 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 120.02389526367188, "min": 73.26654815673828, "max": 120.02389526367188, "count": 2 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751970424618535, "min": 0.06751970424618535, "max": 0.07114582863061501, "count": 2 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6076773382156682, "min": 0.49802080041430513, "max": 0.6076773382156682, "count": 2 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0020629774291683815, "min": 0.0020629774291683815, "max": 0.004938054214438025, "count": 2 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.018566796862515434, "min": 0.018566796862515434, "max": 0.034566379501066176, "count": 2 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.150896505259259e-05, "min": 7.150896505259259e-05, "max": 0.00021917716979809524, "count": 2 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006435806854733333, "min": 0.0006435806854733333, "max": 0.0015342401885866668, "count": 2 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12383629629629632, "min": 0.12383629629629632, "max": 0.1730590476190476, "count": 2 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.1145266666666669, "min": 1.1145266666666669, "max": 1.2114133333333332, "count": 2 }, "Pyramids.Policy.Beta.mean": { "value": 0.0023912460000000005, "min": 0.0023912460000000005, "max": 0.007308598857142857, "count": 2 }, "Pyramids.Policy.Beta.sum": { "value": 0.021521214000000004, "min": 0.021521214000000004, "max": 0.051160192, "count": 2 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.17579102421779083, "min": 0.17579102421779083, "max": 0.4865021553633762, "count": 2 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 1.5821192179601176, "min": 1.5821192179601176, "max": 3.4055150875436335, "count": 2 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.48593344143560446, "min": 0.48593344143560446, "max": 0.7601708495264571, "count": 2 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 4.37340097292044, "min": 4.37340097292044, "max": 5.3211959466852, "count": 2 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 983.7272727272727, "min": 983.7272727272727, "max": 999.0, "count": 2 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32463.0, "min": 15984.0, "max": 32463.0, "count": 2 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.8634485349510655, "min": -1.0000000521540642, "max": -0.8634485349510655, "count": 2 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -28.493801653385162, "min": -28.493801653385162, "max": -16.000000834465027, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.8634485349510655, "min": -1.0000000521540642, "max": -0.8634485349510655, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -28.493801653385162, "min": -28.493801653385162, "max": -16.000000834465027, "count": 2 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 5.174535974860191, "min": 5.174535974860191, "max": 7.066105825826526, "count": 2 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 170.75968717038631, "min": 113.05769321322441, "max": 170.75968717038631, "count": 2 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692966038", "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/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids2 --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": "1692966262" }, "total": 224.27391621100014, "count": 1, "self": 0.6315550570002415, "children": { "run_training.setup": { "total": 0.08380827600012708, "count": 1, "self": 0.08380827600012708 }, "TrainerController.start_learning": { "total": 223.55855287799977, "count": 1, "self": 0.13295064800104228, "children": { "TrainerController._reset_env": { "total": 1.920688992000123, "count": 1, "self": 1.920688992000123 }, "TrainerController.advance": { "total": 221.3474071219989, "count": 3771, "self": 0.1512690069821474, "children": { "env_step": { "total": 115.23695566300967, "count": 3771, "self": 105.65874966700358, "children": { "SubprocessEnvManager._take_step": { "total": 9.493931704998886, "count": 3771, "self": 0.5221308799814324, "children": { "TorchPolicy.evaluate": { "total": 8.971800825017453, "count": 3768, "self": 8.971800825017453 } } }, "workers": { "total": 0.08427429100720474, "count": 3771, "self": 0.0, "children": { "worker_root": { "total": 222.83126691800135, "count": 3771, "is_parallel": true, "self": 127.8539943030014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032852160002221353, "count": 1, "is_parallel": true, "self": 0.0009156420001090737, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023695740001130616, "count": 8, "is_parallel": true, "self": 0.0023695740001130616 } } }, "UnityEnvironment.step": { "total": 0.08681690100002015, "count": 1, "is_parallel": true, "self": 0.0007335120003517659, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006127110000306857, "count": 1, "is_parallel": true, "self": 0.0006127110000306857 }, "communicator.exchange": { "total": 0.08257545699962066, "count": 1, "is_parallel": true, "self": 0.08257545699962066 }, "steps_from_proto": { "total": 0.0028952210000170453, "count": 1, "is_parallel": true, "self": 0.0005566630011344387, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023385579988826066, "count": 8, "is_parallel": true, "self": 0.0023385579988826066 } } } } } } }, "UnityEnvironment.step": { "total": 94.97727261499995, "count": 3770, "is_parallel": true, "self": 2.8577311559938607, "children": { "UnityEnvironment._generate_step_input": { "total": 1.614566963998186, "count": 3770, "is_parallel": true, "self": 1.614566963998186 }, "communicator.exchange": { "total": 81.64266818400392, "count": 3770, "is_parallel": true, "self": 81.64266818400392 }, "steps_from_proto": { "total": 8.862306311003977, "count": 3770, "is_parallel": true, "self": 1.9190092660101072, "children": { "_process_rank_one_or_two_observation": { "total": 6.943297044993869, "count": 30160, "is_parallel": true, "self": 6.943297044993869 } } } } } } } } } } }, "trainer_advance": { "total": 105.9591824520071, "count": 3771, "self": 0.18197155100051532, "children": { "process_trajectory": { "total": 10.691621337007291, "count": 3771, "self": 10.691621337007291 }, "_update_policy": { "total": 95.08558956399929, "count": 16, "self": 57.343644607001806, "children": { "TorchPPOOptimizer.update": { "total": 37.741944956997486, "count": 1356, "self": 37.741944956997486 } } } } } } }, "trainer_threads": { "total": 1.0899998414970469e-06, "count": 1, "self": 1.0899998414970469e-06 }, "TrainerController._save_models": { "total": 0.1575050259998534, "count": 1, "self": 0.0022850939999443654, "children": { "RLTrainer._checkpoint": { "total": 0.15521993199990902, "count": 1, "self": 0.15521993199990902 } } } } } } }