{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2726152241230011, "min": 0.2726152241230011, "max": 1.3210315704345703, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8174.0947265625, "min": 8174.0947265625, "max": 40074.8125, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29913.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29913.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4489189088344574, "min": -0.16955582797527313, "max": 0.5099066495895386, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 121.65702819824219, "min": -40.354286193847656, "max": 138.18470764160156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020386192947626114, "min": 0.007504886016249657, "max": 0.2888573706150055, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.524658203125, "min": 1.9437655210494995, "max": 69.6146240234375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.10212942336744055, "min": 0.09546975780822738, "max": 0.10389953907958836, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.4298119271441676, "min": 0.7975868198331665, "max": 1.5095476898224955, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016125984473801157, "min": 0.0005425480136185609, "max": 0.016125984473801157, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2257637826332162, "min": 0.00596802814980417, "max": 0.2257637826332162, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.562604622021424e-06, "min": 7.562604622021424e-06, "max": 0.00029484941421686255, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010587646470829994, "min": 0.00010587646470829994, "max": 0.0035093405302198994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10504167142857143, "min": 0.10504167142857143, "max": 0.296566275, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4705834, "min": 1.4705834, "max": 3.7395601999999992, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002618314878571427, "min": 0.0002618314878571427, "max": 0.00982848543625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036656408299999984, "min": 0.0036656408299999984, "max": 0.11700103198999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01521213911473751, "min": 0.014662700705230236, "max": 0.44928011298179626, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21296994388103485, "min": 0.20527781546115875, "max": 3.59424090385437, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 398.5061728395062, "min": 398.5061728395062, "max": 989.3939393939394, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32279.0, "min": 17095.0, "max": 32941.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4506374718621373, "min": -0.9297091437108589, "max": 1.487370124058937, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.05099774897099, "min": -30.680401742458344, "max": 116.05099774897099, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4506374718621373, "min": -0.9297091437108589, "max": 1.487370124058937, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.05099774897099, "min": -30.680401742458344, "max": 116.05099774897099, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06476902021152, "min": 0.06440824242475043, "max": 12.136398673781919, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.1815216169216, "min": 4.448290645261295, "max": 218.45517612807453, "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": "1685811844", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685814280" }, "total": 2435.985702387, "count": 1, "self": 0.8902661050005918, "children": { "run_training.setup": { "total": 0.036983322999958546, "count": 1, "self": 0.036983322999958546 }, "TrainerController.start_learning": { "total": 2435.0584529589996, "count": 1, "self": 1.4693754199652176, "children": { "TrainerController._reset_env": { "total": 3.810477206000087, "count": 1, "self": 3.810477206000087 }, "TrainerController.advance": { "total": 2429.6248379260346, "count": 63833, "self": 1.4968542601350237, "children": { "env_step": { "total": 1566.3496836169484, "count": 63833, "self": 1451.9935275581356, "children": { "SubprocessEnvManager._take_step": { "total": 113.4778074308831, "count": 63833, "self": 4.699094630952914, "children": { "TorchPolicy.evaluate": { "total": 108.77871279993019, "count": 62556, "self": 108.77871279993019 } } }, "workers": { "total": 0.878348627929654, "count": 63833, "self": 0.0, "children": { "worker_root": { "total": 2429.8010014839815, "count": 63833, "is_parallel": true, "self": 1092.943982508034, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018823709999651328, "count": 1, "is_parallel": true, "self": 0.0005750989998887235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013072720000764093, "count": 8, "is_parallel": true, "self": 0.0013072720000764093 } } }, "UnityEnvironment.step": { "total": 0.04545763199985231, "count": 1, "is_parallel": true, "self": 0.0005284649998884561, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005016420000174548, "count": 1, "is_parallel": true, "self": 0.0005016420000174548 }, "communicator.exchange": { "total": 0.04268424499991852, "count": 1, "is_parallel": true, "self": 0.04268424499991852 }, "steps_from_proto": { "total": 0.0017432800000278803, "count": 1, "is_parallel": true, "self": 0.00036751300035575696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013757669996721233, "count": 8, "is_parallel": true, "self": 0.0013757669996721233 } } } } } } }, "UnityEnvironment.step": { "total": 1336.8570189759475, "count": 63832, "is_parallel": true, "self": 31.715623885070954, "children": { "UnityEnvironment._generate_step_input": { "total": 22.552964539961977, "count": 63832, "is_parallel": true, "self": 22.552964539961977 }, "communicator.exchange": { "total": 1184.2708989418813, "count": 63832, "is_parallel": true, "self": 1184.2708989418813 }, "steps_from_proto": { "total": 98.31753160903327, "count": 63832, "is_parallel": true, "self": 20.027022954081986, "children": { "_process_rank_one_or_two_observation": { "total": 78.29050865495128, "count": 510656, "is_parallel": true, "self": 78.29050865495128 } } } } } } } } } } }, "trainer_advance": { "total": 861.778300048951, "count": 63833, "self": 2.799217072030615, "children": { "process_trajectory": { "total": 106.01415423392359, "count": 63833, "self": 105.75133278592398, "children": { "RLTrainer._checkpoint": { "total": 0.26282144799961316, "count": 2, "self": 0.26282144799961316 } } }, "_update_policy": { "total": 752.9649287429968, "count": 457, "self": 397.74926873795766, "children": { "TorchPPOOptimizer.update": { "total": 355.2156600050391, "count": 46218, "self": 355.2156600050391 } } } } } } }, "trainer_threads": { "total": 1.2370001059025526e-06, "count": 1, "self": 1.2370001059025526e-06 }, "TrainerController._save_models": { "total": 0.15376116999959777, "count": 1, "self": 0.0019170599998687976, "children": { "RLTrainer._checkpoint": { "total": 0.15184410999972897, "count": 1, "self": 0.15184410999972897 } } } } } } }