{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.26223844289779663, "min": 0.26223844289779663, "max": 1.5016237497329712, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7959.46142578125, "min": 7959.46142578125, "max": 45553.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29928.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29928.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7297298312187195, "min": -0.11346393823623657, "max": 0.7665205001831055, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.35137939453125, "min": -26.890953063964844, "max": 226.8900604248047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01334985252469778, "min": 0.01334985252469778, "max": 0.3806348145008087, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.8848071098327637, "min": 3.8848071098327637, "max": 90.21044921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669987091996951, "min": 0.0664428077372981, "max": 0.07716278828097388, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9379819287957313, "min": 0.5401395179668171, "max": 1.0918941104027908, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014252618569853005, "min": 0.00025940326213510974, "max": 0.01684501042884823, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19953665997794207, "min": 0.0025940326213510973, "max": 0.2358301460038752, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2442347511549997e-05, "min": 1.2442347511549997e-05, "max": 0.0004919177159021714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00017419286516169995, "min": 0.00017419286516169995, "max": 0.005425921314815799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248845, "min": 0.10248845, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348383, "min": 1.3886848, "max": 2.4851842000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025859615499999997, "min": 0.00025859615499999997, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036203461699999993, "min": 0.0036203461699999993, "max": 0.10854990158000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011656478978693485, "min": 0.011656478978693485, "max": 0.4483734667301178, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16319070756435394, "min": 0.16319070756435394, "max": 3.1386141777038574, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 257.02564102564105, "min": 251.8780487804878, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30072.0, "min": 16855.0, "max": 32810.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7245879145017986, "min": -0.9999355356539449, "max": 1.7368695414584616, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 200.05219808220863, "min": -31.997201651334763, "max": 211.01799830794334, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7245879145017986, "min": -0.9999355356539449, "max": 1.7368695414584616, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 200.05219808220863, "min": -31.997201651334763, "max": 211.01799830794334, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031132964077877315, "min": 0.031131029292234557, "max": 9.531955739154535, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6114238330337685, "min": 3.4829676072113216, "max": 162.0432475656271, "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": "1689089521", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --force", "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": "1689092241" }, "total": 2720.112885132, "count": 1, "self": 0.576373902999876, "children": { "run_training.setup": { "total": 0.03923694899998509, "count": 1, "self": 0.03923694899998509 }, "TrainerController.start_learning": { "total": 2719.49727428, "count": 1, "self": 1.9650025169476066, "children": { "TrainerController._reset_env": { "total": 4.513965122999991, "count": 1, "self": 4.513965122999991 }, "TrainerController.advance": { "total": 2712.859167492052, "count": 64298, "self": 2.1395098960106225, "children": { "env_step": { "total": 1945.0356857799825, "count": 64298, "self": 1776.7646584479621, "children": { "SubprocessEnvManager._take_step": { "total": 167.10161059300117, "count": 64298, "self": 6.151154952996649, "children": { "TorchPolicy.evaluate": { "total": 160.95045564000452, "count": 62567, "self": 160.95045564000452 } } }, "workers": { "total": 1.1694167390192547, "count": 64298, "self": 0.0, "children": { "worker_root": { "total": 2712.482012896996, "count": 64298, "is_parallel": true, "self": 1084.8261057429881, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005266584000025887, "count": 1, "is_parallel": true, "self": 0.003891221999992922, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013753620000329647, "count": 8, "is_parallel": true, "self": 0.0013753620000329647 } } }, "UnityEnvironment.step": { "total": 0.053036889999987125, "count": 1, "is_parallel": true, "self": 0.0005849209999837512, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005356819999633444, "count": 1, "is_parallel": true, "self": 0.0005356819999633444 }, "communicator.exchange": { "total": 0.04966543000000456, "count": 1, "is_parallel": true, "self": 0.04966543000000456 }, "steps_from_proto": { "total": 0.0022508570000354666, "count": 1, "is_parallel": true, "self": 0.0004485510000904469, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018023059999450197, "count": 8, "is_parallel": true, "self": 0.0018023059999450197 } } } } } } }, "UnityEnvironment.step": { "total": 1627.6559071540078, "count": 64297, "is_parallel": true, "self": 39.7200046249975, "children": { "UnityEnvironment._generate_step_input": { "total": 27.677611193987218, "count": 64297, "is_parallel": true, "self": 27.677611193987218 }, "communicator.exchange": { "total": 1429.4817182550298, "count": 64297, "is_parallel": true, "self": 1429.4817182550298 }, "steps_from_proto": { "total": 130.7765730799931, "count": 64297, "is_parallel": true, "self": 26.47218245983322, "children": { "_process_rank_one_or_two_observation": { "total": 104.3043906201599, "count": 514376, "is_parallel": true, "self": 104.3043906201599 } } } } } } } } } } }, "trainer_advance": { "total": 765.6839718160592, "count": 64298, "self": 3.553350266059283, "children": { "process_trajectory": { "total": 155.50202164499655, "count": 64298, "self": 155.17933532099636, "children": { "RLTrainer._checkpoint": { "total": 0.3226863240001876, "count": 2, "self": 0.3226863240001876 } } }, "_update_policy": { "total": 606.6285999050033, "count": 447, "self": 383.05958918798564, "children": { "TorchPPOOptimizer.update": { "total": 223.56901071701765, "count": 22815, "self": 223.56901071701765 } } } } } } }, "trainer_threads": { "total": 1.1940001058974303e-06, "count": 1, "self": 1.1940001058974303e-06 }, "TrainerController._save_models": { "total": 0.15913795400001618, "count": 1, "self": 0.0016208260003622854, "children": { "RLTrainer._checkpoint": { "total": 0.1575171279996539, "count": 1, "self": 0.1575171279996539 } } } } } } }