{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6242993474006653, "min": 0.5880316495895386, "max": 1.4737924337387085, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18718.9921875, "min": 17490.4140625, "max": 44708.96875, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3553040325641632, "min": -0.10972978174686432, "max": 0.40684399008750916, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 93.44496154785156, "min": -26.335147857666016, "max": 106.99996948242188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.43233296275138855, "min": -0.5544484853744507, "max": 0.18036147952079773, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -113.70356750488281, "min": -145.8199462890625, "max": 43.46711730957031, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06706181783486727, "min": 0.06568235406694159, "max": 0.0714262509372541, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9388654496881417, "min": 0.49998375656077876, "max": 1.0681767561638447, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.023507221012326687, "min": 9.248941854539661e-05, "max": 0.05741017563050059, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3291010941725736, "min": 0.0012948518596355525, "max": 0.8037424588270082, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.606768893014284e-06, "min": 7.606768893014284e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010649476450219998, "min": 0.00010649476450219998, "max": 0.003606630397789899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253555714285714, "min": 0.10253555714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354978, "min": 1.3886848, "max": 2.5694396, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002633021585714285, "min": 0.0002633021585714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003686230219999999, "min": 0.003686230219999999, "max": 0.12023078898999996, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008979251608252525, "min": 0.008979251608252525, "max": 0.24996042251586914, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12570951879024506, "min": 0.12570951879024506, "max": 1.749722957611084, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 475.5, "min": 437.72857142857146, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29481.0, "min": 15984.0, "max": 33003.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2663483611277995, "min": -1.0000000521540642, "max": 1.3579188213832136, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 78.51359838992357, "min": -29.995401561260223, "max": 93.69639867544174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2663483611277995, "min": -1.0000000521540642, "max": 1.3579188213832136, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 78.51359838992357, "min": -29.995401561260223, "max": 93.69639867544174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04485888970215925, "min": 0.04485888970215925, "max": 4.927146691828966, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7812511615338735, "min": 2.7812511615338735, "max": 78.83434706926346, "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": "1700053865", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700055964" }, "total": 2099.421853189, "count": 1, "self": 0.4759249440003259, "children": { "run_training.setup": { "total": 0.04325087600000188, "count": 1, "self": 0.04325087600000188 }, "TrainerController.start_learning": { "total": 2098.902677369, "count": 1, "self": 1.3535823929655635, "children": { "TrainerController._reset_env": { "total": 3.6051171419999264, "count": 1, "self": 3.6051171419999264 }, "TrainerController.advance": { "total": 2093.8612452730345, "count": 63516, "self": 1.4601919181127414, "children": { "env_step": { "total": 1466.9328852379472, "count": 63516, "self": 1332.8931733649904, "children": { "SubprocessEnvManager._take_step": { "total": 133.18476489199656, "count": 63516, "self": 4.620061537964602, "children": { "TorchPolicy.evaluate": { "total": 128.56470335403196, "count": 62582, "self": 128.56470335403196 } } }, "workers": { "total": 0.8549469809602215, "count": 63516, "self": 0.0, "children": { "worker_root": { "total": 2094.4294233159385, "count": 63516, "is_parallel": true, "self": 881.2619987289875, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028624659998968127, "count": 1, "is_parallel": true, "self": 0.0009668159998454939, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018956500000513188, "count": 8, "is_parallel": true, "self": 0.0018956500000513188 } } }, "UnityEnvironment.step": { "total": 0.10846132699998634, "count": 1, "is_parallel": true, "self": 0.0005965449997802352, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004246420000981743, "count": 1, "is_parallel": true, "self": 0.0004246420000981743 }, "communicator.exchange": { "total": 0.10581949800007351, "count": 1, "is_parallel": true, "self": 0.10581949800007351 }, "steps_from_proto": { "total": 0.0016206420000344224, "count": 1, "is_parallel": true, "self": 0.00032565400010753365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012949879999268887, "count": 8, "is_parallel": true, "self": 0.0012949879999268887 } } } } } } }, "UnityEnvironment.step": { "total": 1213.167424586951, "count": 63515, "is_parallel": true, "self": 34.28781025289413, "children": { "UnityEnvironment._generate_step_input": { "total": 24.51903992704638, "count": 63515, "is_parallel": true, "self": 24.51903992704638 }, "communicator.exchange": { "total": 1053.2671015410147, "count": 63515, "is_parallel": true, "self": 1053.2671015410147 }, "steps_from_proto": { "total": 101.09347286599586, "count": 63515, "is_parallel": true, "self": 20.492807196978674, "children": { "_process_rank_one_or_two_observation": { "total": 80.60066566901719, "count": 508120, "is_parallel": true, "self": 80.60066566901719 } } } } } } } } } } }, "trainer_advance": { "total": 625.4681681169745, "count": 63516, "self": 2.585851397984925, "children": { "process_trajectory": { "total": 121.95422732698876, "count": 63516, "self": 121.79198940898846, "children": { "RLTrainer._checkpoint": { "total": 0.16223791800030085, "count": 2, "self": 0.16223791800030085 } } }, "_update_policy": { "total": 500.92808939200086, "count": 454, "self": 299.1267922780264, "children": { "TorchPPOOptimizer.update": { "total": 201.80129711397444, "count": 22746, "self": 201.80129711397444 } } } } } } }, "trainer_threads": { "total": 9.720001798996236e-07, "count": 1, "self": 9.720001798996236e-07 }, "TrainerController._save_models": { "total": 0.08273158899964983, "count": 1, "self": 0.0014386369994099368, "children": { "RLTrainer._checkpoint": { "total": 0.0812929520002399, "count": 1, "self": 0.0812929520002399 } } } } } } }