{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2865307331085205, "min": 0.2865307331085205, "max": 1.4149564504623413, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8540.908203125, "min": 8540.908203125, "max": 42924.1171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47274520993232727, "min": -0.19388015568256378, "max": 0.5382140278816223, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.16846466064453, "min": -45.9495964050293, "max": 148.5470733642578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007173711899667978, "min": 0.002500066999346018, "max": 0.6946797370910645, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9297285079956055, "min": 0.6725180149078369, "max": 164.63909912109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0655152004212141, "min": 0.0655152004212141, "max": 0.07491459351251326, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9827280063182116, "min": 0.5238796527927002, "max": 1.0753788167009284, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015727340592679363, "min": 0.00020684231200680908, "max": 0.016012362470298924, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23591010889019043, "min": 0.0022752654320749, "max": 0.23591010889019043, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.519957493379998e-06, "min": 7.519957493379998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011279936240069997, "min": 0.00011279936240069997, "max": 0.0032556471147844, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250662, "min": 0.10250662, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375993000000001, "min": 1.3886848, "max": 2.5275456000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000260411338, "min": 0.000260411338, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00390617007, "min": 0.00390617007, "max": 0.10855303844, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00717059476301074, "min": 0.00717059476301074, "max": 0.518469512462616, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10755892097949982, "min": 0.10665935277938843, "max": 3.629286527633667, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 372.2098765432099, "min": 339.2168674698795, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30149.0, "min": 15984.0, "max": 32383.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.478707298454715, "min": -1.0000000521540642, "max": 1.6380190343729086, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.25399847328663, "min": -31.99920167028904, "max": 137.59359888732433, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.478707298454715, "min": -1.0000000521540642, "max": 1.6380190343729086, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.25399847328663, "min": -31.99920167028904, "max": 137.59359888732433, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02804278771651386, "min": 0.027479513129427296, "max": 11.071777628734708, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2995085927541368, "min": 2.2995085927541368, "max": 177.14844205975533, "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": "1693754577", "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 --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": "1693756755" }, "total": 2178.7150572440005, "count": 1, "self": 0.5268930880006337, "children": { "run_training.setup": { "total": 0.05170946399994136, "count": 1, "self": 0.05170946399994136 }, "TrainerController.start_learning": { "total": 2178.136454692, "count": 1, "self": 1.3922886390969325, "children": { "TrainerController._reset_env": { "total": 4.195742909000046, "count": 1, "self": 4.195742909000046 }, "TrainerController.advance": { "total": 2172.451186598903, "count": 63746, "self": 1.3794617288954214, "children": { "env_step": { "total": 1518.4770248770392, "count": 63746, "self": 1409.3409154951294, "children": { "SubprocessEnvManager._take_step": { "total": 108.29411246392146, "count": 63746, "self": 4.615468237866935, "children": { "TorchPolicy.evaluate": { "total": 103.67864422605453, "count": 62557, "self": 103.67864422605453 } } }, "workers": { "total": 0.8419969179883537, "count": 63746, "self": 0.0, "children": { "worker_root": { "total": 2173.4163545009897, "count": 63746, "is_parallel": true, "self": 876.9521411079927, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016933300000800955, "count": 1, "is_parallel": true, "self": 0.000495365000460879, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011979649996192165, "count": 8, "is_parallel": true, "self": 0.0011979649996192165 } } }, "UnityEnvironment.step": { "total": 0.05049276600016128, "count": 1, "is_parallel": true, "self": 0.000588400000196998, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005149620001247968, "count": 1, "is_parallel": true, "self": 0.0005149620001247968 }, "communicator.exchange": { "total": 0.047484227000040846, "count": 1, "is_parallel": true, "self": 0.047484227000040846 }, "steps_from_proto": { "total": 0.0019051769997986412, "count": 1, "is_parallel": true, "self": 0.0003731109998170723, "children": { "_process_rank_one_or_two_observation": { "total": 0.001532065999981569, "count": 8, "is_parallel": true, "self": 0.001532065999981569 } } } } } } }, "UnityEnvironment.step": { "total": 1296.464213392997, "count": 63745, "is_parallel": true, "self": 33.85473085606782, "children": { "UnityEnvironment._generate_step_input": { "total": 22.758275278991505, "count": 63745, "is_parallel": true, "self": 22.758275278991505 }, "communicator.exchange": { "total": 1135.4116592869839, "count": 63745, "is_parallel": true, "self": 1135.4116592869839 }, "steps_from_proto": { "total": 104.43954797095375, "count": 63745, "is_parallel": true, "self": 20.338374040010194, "children": { "_process_rank_one_or_two_observation": { "total": 84.10117393094356, "count": 509960, "is_parallel": true, "self": 84.10117393094356 } } } } } } } } } } }, "trainer_advance": { "total": 652.5946999929681, "count": 63746, "self": 2.6568288640100945, "children": { "process_trajectory": { "total": 108.50572413695545, "count": 63746, "self": 108.2961990409558, "children": { "RLTrainer._checkpoint": { "total": 0.20952509599965197, "count": 2, "self": 0.20952509599965197 } } }, "_update_policy": { "total": 541.4321469920026, "count": 447, "self": 352.09000334299526, "children": { "TorchPPOOptimizer.update": { "total": 189.3421436490073, "count": 22779, "self": 189.3421436490073 } } } } } } }, "trainer_threads": { "total": 9.149998732027598e-07, "count": 1, "self": 9.149998732027598e-07 }, "TrainerController._save_models": { "total": 0.09723562999988644, "count": 1, "self": 0.0014273089996095223, "children": { "RLTrainer._checkpoint": { "total": 0.09580832100027692, "count": 1, "self": 0.09580832100027692 } } } } } } }