{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1612342894077301, "min": 0.16044925153255463, "max": 1.5055969953536987, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4855.0869140625, "min": 4786.6044921875, "max": 45673.7890625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999982.0, "min": 29952.0, "max": 2999982.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999982.0, "min": 29952.0, "max": 2999982.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7085379362106323, "min": -0.19641873240470886, "max": 0.8123100996017456, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 202.641845703125, "min": -46.551239013671875, "max": 244.50534057617188, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0028791080694645643, "min": -0.015680436044931412, "max": 0.2527826726436615, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8234248757362366, "min": -4.202356815338135, "max": 60.920623779296875, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848906578882683, "min": 0.06418875267263503, "max": 0.07328422991828443, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9588469210435755, "min": 0.512989609427991, "max": 1.0898607728498368, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015294806196544114, "min": 0.0003168153248474488, "max": 0.016712395944133665, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2141272867516176, "min": 0.004118599223016835, "max": 0.248573215668633, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5003923570452305e-06, "min": 1.5003923570452305e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1005492998633226e-05, "min": 2.1005492998633226e-05, "max": 0.0038924390025204, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050009761904762, "min": 0.10050009761904762, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4070013666666665, "min": 1.3962282666666668, "max": 2.7974796, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.995975214285689e-05, "min": 5.995975214285689e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008394365299999964, "min": 0.0008394365299999964, "max": 0.12976821204, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005940557457506657, "min": 0.005703814793378115, "max": 0.38410019874572754, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08316780626773834, "min": 0.07985340803861618, "max": 2.6887013912200928, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.9339622641509, "min": 229.2890625, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30627.0, "min": 15984.0, "max": 32735.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6154095043738683, "min": -1.0000000521540642, "max": 1.7707109276670963, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 169.61799795925617, "min": -30.996801629662514, "max": 226.65099874138832, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6154095043738683, "min": -1.0000000521540642, "max": 1.7707109276670963, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 169.61799795925617, "min": -30.996801629662514, "max": 226.65099874138832, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017755818990103547, "min": 0.014413899790970838, "max": 7.108289192430675, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8643609939608723, "min": 1.7584957744984422, "max": 113.7326270788908, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701700606", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701711249" }, "total": 10643.120320305, "count": 1, "self": 0.9091790870006662, "children": { "run_training.setup": { "total": 0.08018456600029822, "count": 1, "self": 0.08018456600029822 }, "TrainerController.start_learning": { "total": 10642.130956652, "count": 1, "self": 7.065394842349633, "children": { "TrainerController._reset_env": { "total": 5.05542832600031, "count": 1, "self": 5.05542832600031 }, "TrainerController.advance": { "total": 10629.910457259648, "count": 194663, "self": 7.517806309992011, "children": { "env_step": { "total": 7326.748858977803, "count": 194663, "self": 6855.945055302728, "children": { "SubprocessEnvManager._take_step": { "total": 466.39623372700953, "count": 194663, "self": 20.682901619070435, "children": { "TorchPolicy.evaluate": { "total": 445.7133321079391, "count": 187564, "self": 445.7133321079391 } } }, "workers": { "total": 4.407569948065429, "count": 194663, "self": 0.0, "children": { "worker_root": { "total": 10623.37080197717, "count": 194663, "is_parallel": true, "self": 4301.8024408132305, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009009202000015648, "count": 1, "is_parallel": true, "self": 0.005549945000439038, "children": { "_process_rank_one_or_two_observation": { "total": 0.00345925699957661, "count": 8, "is_parallel": true, "self": 0.00345925699957661 } } }, "UnityEnvironment.step": { "total": 0.18599794200008546, "count": 1, "is_parallel": true, "self": 0.0007788800003254437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005291739998938283, "count": 1, "is_parallel": true, "self": 0.0005291739998938283 }, "communicator.exchange": { "total": 0.17924399599996832, "count": 1, "is_parallel": true, "self": 0.17924399599996832 }, "steps_from_proto": { "total": 0.005445891999897867, "count": 1, "is_parallel": true, "self": 0.0004777950007337495, "children": { "_process_rank_one_or_two_observation": { "total": 0.004968096999164118, "count": 8, "is_parallel": true, "self": 0.004968096999164118 } } } } } } }, "UnityEnvironment.step": { "total": 6321.568361163939, "count": 194662, "is_parallel": true, "self": 142.74965118489035, "children": { "UnityEnvironment._generate_step_input": { "total": 85.33503617702809, "count": 194662, "is_parallel": true, "self": 85.33503617702809 }, "communicator.exchange": { "total": 5702.920206505953, "count": 194662, "is_parallel": true, "self": 5702.920206505953 }, "steps_from_proto": { "total": 390.5634672960673, "count": 194662, "is_parallel": true, "self": 82.67802912121851, "children": { "_process_rank_one_or_two_observation": { "total": 307.8854381748488, "count": 1557296, "is_parallel": true, "self": 307.8854381748488 } } } } } } } } } } }, "trainer_advance": { "total": 3295.6437919718533, "count": 194663, "self": 14.156807409042358, "children": { "process_trajectory": { "total": 510.9637067727922, "count": 194663, "self": 510.30718005979315, "children": { "RLTrainer._checkpoint": { "total": 0.6565267129990389, "count": 6, "self": 0.6565267129990389 } } }, "_update_policy": { "total": 2770.5232777900187, "count": 1396, "self": 1170.9103041874296, "children": { "TorchPPOOptimizer.update": { "total": 1599.6129736025891, "count": 68367, "self": 1599.6129736025891 } } } } } } }, "trainer_threads": { "total": 1.0330004442948848e-06, "count": 1, "self": 1.0330004442948848e-06 }, "TrainerController._save_models": { "total": 0.09967519100064237, "count": 1, "self": 0.002583217999927001, "children": { "RLTrainer._checkpoint": { "total": 0.09709197300071537, "count": 1, "self": 0.09709197300071537 } } } } } } }