{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34481528401374817, "min": 0.34481528401374817, "max": 1.5018041133880615, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10322.390625, "min": 10322.390625, "max": 45558.73046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29926.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29926.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46803978085517883, "min": -0.10783828794956207, "max": 0.5152405500411987, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.77485656738281, "min": -25.98902702331543, "max": 140.66067504882812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022734254598617554, "min": 0.008233049884438515, "max": 0.3087581694126129, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.206451416015625, "min": 2.1570589542388916, "max": 73.48444366455078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.09693231751265963, "min": 0.09273901670389165, "max": 0.10236737163614937, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.3570524451772348, "min": 0.8035499883343974, "max": 1.4783488362220265, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015311478454094517, "min": 8.235506511971757e-05, "max": 0.016295559956715427, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21436069835732324, "min": 0.0009059057163168933, "max": 0.22813783939401597, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2601240336914283e-05, "min": 1.2601240336914283e-05, "max": 0.00049215325156935, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00017641736471679998, "min": 0.00017641736471679998, "max": 0.005552602089479599, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252022857142858, "min": 0.10252022857142858, "max": 0.19843065, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352832, "min": 1.4352832, "max": 2.4429831, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002617708342857143, "min": 0.0002617708342857143, "max": 0.009843221935, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036647916799999996, "min": 0.0036647916799999996, "max": 0.11106098795999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011676467955112457, "min": 0.011627065017819405, "max": 0.3457539677619934, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1634705513715744, "min": 0.16277891397476196, "max": 2.7660317420959473, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 365.5487804878049, "min": 365.5487804878049, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29975.0, "min": 15957.0, "max": 33699.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5368536453603245, "min": -0.9999500522390008, "max": 1.5368536453603245, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.0219989195466, "min": -31.998401671648026, "max": 126.75319854915142, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5368536453603245, "min": -0.9999500522390008, "max": 1.5368536453603245, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.0219989195466, "min": -31.998401671648026, "max": 126.75319854915142, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04503406935638362, "min": 0.04503406935638362, "max": 8.312604990952154, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.692793687223457, "min": 3.568272590113338, "max": 141.31428484618664, "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": "1746107405", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746111309" }, "total": 3904.1241378269997, "count": 1, "self": 0.6940541089998078, "children": { "run_training.setup": { "total": 0.04962710299992068, "count": 1, "self": 0.04962710299992068 }, "TrainerController.start_learning": { "total": 3903.3804566149997, "count": 1, "self": 2.609234271031255, "children": { "TrainerController._reset_env": { "total": 4.810478654999997, "count": 1, "self": 4.810478654999997 }, "TrainerController.advance": { "total": 3895.876664252968, "count": 63555, "self": 2.905942025765853, "children": { "env_step": { "total": 2324.0779126541593, "count": 63555, "self": 2140.225011171068, "children": { "SubprocessEnvManager._take_step": { "total": 182.39800204096446, "count": 63555, "self": 8.352170253959684, "children": { "TorchPolicy.evaluate": { "total": 174.04583178700477, "count": 62564, "self": 174.04583178700477 } } }, "workers": { "total": 1.4548994421265888, "count": 63555, "self": 0.0, "children": { "worker_root": { "total": 3894.6394869369406, "count": 63555, "is_parallel": true, "self": 1951.824779196955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007061886999963463, "count": 1, "is_parallel": true, "self": 0.00488538800027527, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021764989996881923, "count": 8, "is_parallel": true, "self": 0.0021764989996881923 } } }, "UnityEnvironment.step": { "total": 0.06526325799995902, "count": 1, "is_parallel": true, "self": 0.0007523859999309934, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005498610000813642, "count": 1, "is_parallel": true, "self": 0.0005498610000813642 }, "communicator.exchange": { "total": 0.059402432999831944, "count": 1, "is_parallel": true, "self": 0.059402432999831944 }, "steps_from_proto": { "total": 0.004558578000114721, "count": 1, "is_parallel": true, "self": 0.0029789350005557935, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015796429995589278, "count": 8, "is_parallel": true, "self": 0.0015796429995589278 } } } } } } }, "UnityEnvironment.step": { "total": 1942.8147077399856, "count": 63554, "is_parallel": true, "self": 50.913178145112624, "children": { "UnityEnvironment._generate_step_input": { "total": 33.525055799940446, "count": 63554, "is_parallel": true, "self": 33.525055799940446 }, "communicator.exchange": { "total": 1722.8243768189602, "count": 63554, "is_parallel": true, "self": 1722.8243768189602 }, "steps_from_proto": { "total": 135.5520969759723, "count": 63554, "is_parallel": true, "self": 29.944004601915594, "children": { "_process_rank_one_or_two_observation": { "total": 105.6080923740567, "count": 508432, "is_parallel": true, "self": 105.6080923740567 } } } } } } } } } } }, "trainer_advance": { "total": 1568.892809573043, "count": 63555, "self": 5.2052408990618915, "children": { "process_trajectory": { "total": 178.68207197198058, "count": 63555, "self": 178.15663985898095, "children": { "RLTrainer._checkpoint": { "total": 0.5254321129996242, "count": 2, "self": 0.5254321129996242 } } }, "_update_policy": { "total": 1385.0054967020005, "count": 450, "self": 475.1172797279678, "children": { "TorchPPOOptimizer.update": { "total": 909.8882169740327, "count": 46248, "self": 909.8882169740327 } } } } } } }, "trainer_threads": { "total": 1.1830006769741885e-06, "count": 1, "self": 1.1830006769741885e-06 }, "TrainerController._save_models": { "total": 0.08407825299946126, "count": 1, "self": 0.0017922589995578164, "children": { "RLTrainer._checkpoint": { "total": 0.08228599399990344, "count": 1, "self": 0.08228599399990344 } } } } } } }