{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7858392596244812, "min": 0.777685821056366, "max": 1.4309501647949219, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 23675.765625, "min": 23293.24609375, "max": 43409.3046875, "count": 10 }, "Pyramids.Step.mean": { "value": 299914.0, "min": 29985.0, "max": 299914.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299914.0, "min": 29985.0, "max": 299914.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.056226834654808044, "min": -0.10869290679693222, "max": -0.015005527064204216, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -13.606893539428711, "min": -25.868911743164062, "max": -3.661348581314087, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03420837223529816, "min": 0.03420837223529816, "max": 0.31699976325035095, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.278426170349121, "min": 8.278426170349121, "max": 76.07994079589844, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06854062859099899, "min": 0.06518113792651198, "max": 0.07094090310328148, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9595688002739858, "min": 0.49658632172297035, "max": 0.9595688002739858, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0026313520920953236, "min": 0.0013577731329034249, "max": 0.009001368930946985, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.03683892928933453, "min": 0.013577731329034249, "max": 0.0630095825166289, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5808809016142854e-05, "min": 1.5808809016142854e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00022132332622599996, "min": 0.00022132332622599996, "max": 0.0025542941485686664, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10526957142857143, "min": 0.10526957142857143, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4737740000000001, "min": 1.362282666666667, "max": 2.1700253333333337, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005364301857142856, "min": 0.0005364301857142856, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.007510022599999998, "min": 0.007510022599999998, "max": 0.08515799019999999, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.029853543266654015, "min": 0.029853543266654015, "max": 0.4086994230747223, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4179496169090271, "min": 0.4179496169090271, "max": 2.860895872116089, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 921.59375, "min": 921.59375, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29491.0, "min": 16784.0, "max": 32392.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5471437945961952, "min": -0.9999936006722911, "max": -0.5072187976911664, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -17.508601427078247, "min": -30.999801620841026, "max": -14.800000816583633, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5471437945961952, "min": -0.9999936006722911, "max": -0.5072187976911664, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -17.508601427078247, "min": -30.999801620841026, "max": -14.800000816583633, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.28680013300618157, "min": 0.28680013300618157, "max": 8.059857618282823, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 9.17760425619781, "min": 9.17760425619781, "max": 137.017579510808, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744946338", "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=PyramidsTraining --no-graphics", "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": "1744946972" }, "total": 634.239540109, "count": 1, "self": 0.4757292280000911, "children": { "run_training.setup": { "total": 0.02012679300014497, "count": 1, "self": 0.02012679300014497 }, "TrainerController.start_learning": { "total": 633.7436840879998, "count": 1, "self": 0.42455023297566186, "children": { "TrainerController._reset_env": { "total": 2.5723069450000366, "count": 1, "self": 2.5723069450000366 }, "TrainerController.advance": { "total": 630.6358645630239, "count": 18941, "self": 0.4448395930173774, "children": { "env_step": { "total": 421.32257905800293, "count": 18941, "self": 372.4812686039693, "children": { "SubprocessEnvManager._take_step": { "total": 48.58424839700547, "count": 18941, "self": 1.4271301689707343, "children": { "TorchPolicy.evaluate": { "total": 47.15711822803473, "count": 18814, "self": 47.15711822803473 } } }, "workers": { "total": 0.25706205702817897, "count": 18941, "self": 0.0, "children": { "worker_root": { "total": 632.2065439160008, "count": 18941, "is_parallel": true, "self": 294.163301254021, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024063050000222574, "count": 1, "is_parallel": true, "self": 0.0007741700001133722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016321349999088852, "count": 8, "is_parallel": true, "self": 0.0016321349999088852 } } }, "UnityEnvironment.step": { "total": 0.08101436799984185, "count": 1, "is_parallel": true, "self": 0.0005548459998863109, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040213499983110523, "count": 1, "is_parallel": true, "self": 0.00040213499983110523 }, "communicator.exchange": { "total": 0.07849305000013374, "count": 1, "is_parallel": true, "self": 0.07849305000013374 }, "steps_from_proto": { "total": 0.0015643369999907009, "count": 1, "is_parallel": true, "self": 0.000323436999678961, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012409000003117399, "count": 8, "is_parallel": true, "self": 0.0012409000003117399 } } } } } } }, "UnityEnvironment.step": { "total": 338.0432426619798, "count": 18940, "is_parallel": true, "self": 9.697239350983637, "children": { "UnityEnvironment._generate_step_input": { "total": 6.9463453119999485, "count": 18940, "is_parallel": true, "self": 6.9463453119999485 }, "communicator.exchange": { "total": 292.54613335397585, "count": 18940, "is_parallel": true, "self": 292.54613335397585 }, "steps_from_proto": { "total": 28.853524645020343, "count": 18940, "is_parallel": true, "self": 5.826960553031768, "children": { "_process_rank_one_or_two_observation": { "total": 23.026564091988575, "count": 151520, "is_parallel": true, "self": 23.026564091988575 } } } } } } } } } } }, "trainer_advance": { "total": 208.8684459120036, "count": 18941, "self": 0.7041200009784916, "children": { "process_trajectory": { "total": 37.19802352402485, "count": 18941, "self": 37.19802352402485 }, "_update_policy": { "total": 170.96630238700027, "count": 122, "self": 95.49720517900505, "children": { "TorchPPOOptimizer.update": { "total": 75.46909720799522, "count": 6849, "self": 75.46909720799522 } } } } } } }, "trainer_threads": { "total": 9.620000582799548e-07, "count": 1, "self": 9.620000582799548e-07 }, "TrainerController._save_models": { "total": 0.11096138500010966, "count": 1, "self": 0.0013465420001921302, "children": { "RLTrainer._checkpoint": { "total": 0.10961484299991753, "count": 1, "self": 0.10961484299991753 } } } } } } }