{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6246396899223328, "min": 0.6197971105575562, "max": 1.5126522779464722, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18829.138671875, "min": 18445.162109375, "max": 45887.8203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989967.0, "min": 29952.0, "max": 989967.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5144776105880737, "min": -0.15559345483779907, "max": 0.5316869616508484, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 140.452392578125, "min": -37.342430114746094, "max": 147.27728271484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.07305539399385452, "min": -0.07305539399385452, "max": 0.21210691332817078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -19.944122314453125, "min": -19.944122314453125, "max": 50.90565872192383, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06673389749942414, "min": 0.06384169656338677, "max": 0.07474782599837496, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.934274564991938, "min": 0.4980725438712732, "max": 1.0650872443460258, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012759620974109221, "min": 6.04095597939952e-05, "max": 0.013907077075384137, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1786346936375291, "min": 0.0008457338371159328, "max": 0.20834170208827876, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.451861801792859e-06, "min": 7.451861801792859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010432606522510002, "min": 0.00010432606522510002, "max": 0.0035071934309355997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248392142857143, "min": 0.10248392142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347749, "min": 1.3886848, "max": 2.5690644, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025814375071428583, "min": 0.00025814375071428583, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036140125100000016, "min": 0.0036140125100000016, "max": 0.11692953356, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008529199287295341, "min": 0.008438932709395885, "max": 0.37847355008125305, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11940878629684448, "min": 0.11814506351947784, "max": 2.6493148803710938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.2151898734177, "min": 364.44444444444446, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29563.0, "min": 15984.0, "max": 32728.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6004582058779802, "min": -1.0000000521540642, "max": 1.6004582058779802, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 126.43619826436043, "min": -30.999801620841026, "max": 128.47859855741262, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6004582058779802, "min": -1.0000000521540642, "max": 1.6004582058779802, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 126.43619826436043, "min": -30.999801620841026, "max": 128.47859855741262, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03337040053469813, "min": 0.03337040053469813, "max": 7.749784346669912, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.636261642241152, "min": 2.636261642241152, "max": 123.9965495467186, "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": "1698498925", "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 2 --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": "1698501039" }, "total": 2114.1815712210005, "count": 1, "self": 1.1427680160009004, "children": { "run_training.setup": { "total": 0.052593939999951544, "count": 1, "self": 0.052593939999951544 }, "TrainerController.start_learning": { "total": 2112.9862092649996, "count": 1, "self": 1.2166943039087528, "children": { "TrainerController._reset_env": { "total": 3.8433889519997138, "count": 1, "self": 3.8433889519997138 }, "TrainerController.advance": { "total": 2107.814769991091, "count": 63558, "self": 1.3189337740109295, "children": { "env_step": { "total": 1478.7869760530716, "count": 63558, "self": 1351.3888449880378, "children": { "SubprocessEnvManager._take_step": { "total": 126.62905455390728, "count": 63558, "self": 4.502868956939437, "children": { "TorchPolicy.evaluate": { "total": 122.12618559696784, "count": 62560, "self": 122.12618559696784 } } }, "workers": { "total": 0.7690765111265137, "count": 63558, "self": 0.0, "children": { "worker_root": { "total": 2108.462496060061, "count": 63558, "is_parallel": true, "self": 866.6521580960743, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022104560002844664, "count": 1, "is_parallel": true, "self": 0.0006285180011218472, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015819379991626192, "count": 8, "is_parallel": true, "self": 0.0015819379991626192 } } }, "UnityEnvironment.step": { "total": 0.09347373400032666, "count": 1, "is_parallel": true, "self": 0.0006404179998753534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048926300041785, "count": 1, "is_parallel": true, "self": 0.00048926300041785 }, "communicator.exchange": { "total": 0.09065824900017105, "count": 1, "is_parallel": true, "self": 0.09065824900017105 }, "steps_from_proto": { "total": 0.0016858039998624008, "count": 1, "is_parallel": true, "self": 0.00037898600021435414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013068179996480467, "count": 8, "is_parallel": true, "self": 0.0013068179996480467 } } } } } } }, "UnityEnvironment.step": { "total": 1241.8103379639865, "count": 63557, "is_parallel": true, "self": 34.379278015023374, "children": { "UnityEnvironment._generate_step_input": { "total": 23.919968506048008, "count": 63557, "is_parallel": true, "self": 23.919968506048008 }, "communicator.exchange": { "total": 1086.5193277379803, "count": 63557, "is_parallel": true, "self": 1086.5193277379803 }, "steps_from_proto": { "total": 96.99176370493478, "count": 63557, "is_parallel": true, "self": 18.971812437144763, "children": { "_process_rank_one_or_two_observation": { "total": 78.01995126779002, "count": 508456, "is_parallel": true, "self": 78.01995126779002 } } } } } } } } } } }, "trainer_advance": { "total": 627.7088601640085, "count": 63558, "self": 2.47260705603685, "children": { "process_trajectory": { "total": 118.36777949097814, "count": 63558, "self": 118.16682913497789, "children": { "RLTrainer._checkpoint": { "total": 0.20095035600024858, "count": 2, "self": 0.20095035600024858 } } }, "_update_policy": { "total": 506.86847361699347, "count": 450, "self": 302.4250503361309, "children": { "TorchPPOOptimizer.update": { "total": 204.4434232808626, "count": 22779, "self": 204.4434232808626 } } } } } } }, "trainer_threads": { "total": 1.247000000148546e-06, "count": 1, "self": 1.247000000148546e-06 }, "TrainerController._save_models": { "total": 0.11135477100015123, "count": 1, "self": 0.001853171999755432, "children": { "RLTrainer._checkpoint": { "total": 0.1095015990003958, "count": 1, "self": 0.1095015990003958 } } } } } } }