{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5708699822425842, "min": 0.5708699822425842, "max": 1.5417309999465942, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17144.3671875, "min": 17144.3671875, "max": 46769.953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989943.0, "min": 29952.0, "max": 989943.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05284634977579117, "min": -0.09831222891807556, "max": 0.06268835067749023, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 12.894509315490723, "min": -23.693246841430664, "max": 15.233268737792969, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0025327419862151146, "min": 0.0025327419862151146, "max": 0.18176408112049103, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6179890632629395, "min": 0.6179890632629395, "max": 43.078086853027344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.13629314735778095, "min": 0.1306943559024466, "max": 0.1492144265051077, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 2.0443972103667143, "min": 0.9850428738347232, "max": 2.0564164466948096, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0037154096802173883, "min": 1.2028345910264857e-05, "max": 0.0038143186133076136, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05573114520326083, "min": 0.00015636849683344314, "max": 0.05573114520326083, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.531077489673336e-06, "min": 7.531077489673336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011296616234510004, "min": 0.00011296616234510004, "max": 0.0033709783763406, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251032666666668, "min": 0.10251032666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376549000000002, "min": 1.3691136000000002, "max": 2.4236594000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607816340000001, "min": 0.0002607816340000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039117245100000015, "min": 0.0039117245100000015, "max": 0.11238357405999996, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.002305775647982955, "min": 0.002305775647982955, "max": 0.0496012307703495, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.03458663448691368, "min": 0.032689835876226425, "max": 0.3472086191177368, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 839.2222222222222, "min": 823.6969696969697, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30212.0, "min": 15984.0, "max": 32758.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.1174278271694978, "min": -1.0000000521540642, "max": -0.06450593208565432, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -4.227401778101921, "min": -32.000001668930054, "max": -2.1932016909122467, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.1174278271694978, "min": -1.0000000521540642, "max": -0.06450593208565432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -4.227401778101921, "min": -32.000001668930054, "max": -2.1932016909122467, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02464868994179091, "min": 0.02464868994179091, "max": 3.899521377723431, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 0.8873528379044728, "min": 0.8586896556953434, "max": 62.3923420435749, "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": "1739421261", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739430259" }, "total": 8997.871636274002, "count": 1, "self": 0.6377635150020069, "children": { "run_training.setup": { "total": 0.028000285000416625, "count": 1, "self": 0.028000285000416625 }, "TrainerController.start_learning": { "total": 8997.205872473998, "count": 1, "self": 2.309451950031871, "children": { "TrainerController._reset_env": { "total": 3.065918163999413, "count": 1, "self": 3.065918163999413 }, "TrainerController.advance": { "total": 8991.746659109966, "count": 63166, "self": 2.6027346748669515, "children": { "env_step": { "total": 1785.149796195018, "count": 63166, "self": 1615.4986482201475, "children": { "SubprocessEnvManager._take_step": { "total": 168.29640332503732, "count": 63166, "self": 7.068450350054263, "children": { "TorchPolicy.evaluate": { "total": 161.22795297498305, "count": 62564, "self": 161.22795297498305 } } }, "workers": { "total": 1.3547446498332647, "count": 63166, "self": 0.0, "children": { "worker_root": { "total": 8990.315897837005, "count": 63166, "is_parallel": true, "self": 7547.556474579211, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003094344000601268, "count": 1, "is_parallel": true, "self": 0.000881360000676068, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022129839999252, "count": 8, "is_parallel": true, "self": 0.0022129839999252 } } }, "UnityEnvironment.step": { "total": 0.09327848900011304, "count": 1, "is_parallel": true, "self": 0.0006488999997600331, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005738550007663434, "count": 1, "is_parallel": true, "self": 0.0005738550007663434 }, "communicator.exchange": { "total": 0.09008829399954266, "count": 1, "is_parallel": true, "self": 0.09008829399954266 }, "steps_from_proto": { "total": 0.0019674400000440073, "count": 1, "is_parallel": true, "self": 0.00047225499838532414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014951850016586832, "count": 8, "is_parallel": true, "self": 0.0014951850016586832 } } } } } } }, "UnityEnvironment.step": { "total": 1442.759423257794, "count": 63165, "is_parallel": true, "self": 44.107836898750975, "children": { "UnityEnvironment._generate_step_input": { "total": 30.747484571862515, "count": 63165, "is_parallel": true, "self": 30.747484571862515 }, "communicator.exchange": { "total": 1242.6184983570183, "count": 63165, "is_parallel": true, "self": 1242.6184983570183 }, "steps_from_proto": { "total": 125.28560343016215, "count": 63165, "is_parallel": true, "self": 27.168742916220253, "children": { "_process_rank_one_or_two_observation": { "total": 98.1168605139419, "count": 505320, "is_parallel": true, "self": 98.1168605139419 } } } } } } } } } } }, "trainer_advance": { "total": 7203.9941282400805, "count": 63166, "self": 4.602254039779837, "children": { "process_trajectory": { "total": 163.6972787543, "count": 63166, "self": 163.48777815430003, "children": { "RLTrainer._checkpoint": { "total": 0.20950059999995574, "count": 2, "self": 0.20950059999995574 } } }, "_update_policy": { "total": 7035.694595446001, "count": 439, "self": 2027.1261700761625, "children": { "TorchPPOOptimizer.update": { "total": 5008.568425369838, "count": 310530, "self": 5008.568425369838 } } } } } } }, "trainer_threads": { "total": 1.1040010576834902e-06, "count": 1, "self": 1.1040010576834902e-06 }, "TrainerController._save_models": { "total": 0.08384214599936968, "count": 1, "self": 0.003034474999367376, "children": { "RLTrainer._checkpoint": { "total": 0.0808076710000023, "count": 1, "self": 0.0808076710000023 } } } } } } }