{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4572785198688507, "min": 0.4572785198688507, "max": 1.4808874130249023, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13718.35546875, "min": 13718.35546875, "max": 44924.19921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989986.0, "min": 29948.0, "max": 989986.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989986.0, "min": 29948.0, "max": 989986.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5606920719146729, "min": -0.12153805792331696, "max": 0.5956540703773499, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.62962341308594, "min": -29.290672302246094, "max": 164.99618530273438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.016651514917612076, "min": -0.016651514917612076, "max": 0.35181012749671936, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.5625152587890625, "min": -4.5625152587890625, "max": 83.37899780273438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06474674562923609, "min": 0.06474674562923609, "max": 0.07451072906083639, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9064544388093053, "min": 0.5960858324866911, "max": 1.0324346650741063, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.020385229790311616, "min": 0.00014876859912379476, "max": 0.020385229790311616, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2853932170643626, "min": 0.0020827603877331268, "max": 0.2853932170643626, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.475368936814284e-06, "min": 7.475368936814284e-06, "max": 0.00029484045171985, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010465516511539997, "min": 0.00010465516511539997, "max": 0.0035084306305231995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249175714285716, "min": 0.10249175714285716, "max": 0.19828015, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348846000000002, "min": 1.4348846000000002, "max": 2.5694768000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025892653857142854, "min": 0.00025892653857142854, "max": 0.009828186985000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036249715399999994, "min": 0.0036249715399999994, "max": 0.11697073231999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009819108061492443, "min": 0.009819108061492443, "max": 0.4259154498577118, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13746751844882965, "min": 0.13746751844882965, "max": 3.4073235988616943, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.97701149425285, "min": 308.752688172043, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29491.0, "min": 16491.0, "max": 32611.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5920482517658978, "min": -0.9998375521972775, "max": 1.620035403020059, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 138.50819790363312, "min": -31.99480167031288, "max": 155.52339868992567, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5920482517658978, "min": -0.9998375521972775, "max": 1.620035403020059, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 138.50819790363312, "min": -31.99480167031288, "max": 155.52339868992567, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03453781216033338, "min": 0.03319702468666327, "max": 9.299577751580406, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0047896579490043, "min": 3.0047896579490043, "max": 158.0928217768669, "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": "1741333890", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/dbarbashin/venvs_user/rl_huggi/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining2 --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": "1741335254" }, "total": 1318.3630437140237, "count": 1, "self": 0.2186361019848846, "children": { "run_training.setup": { "total": 0.015254408004693687, "count": 1, "self": 0.015254408004693687 }, "TrainerController.start_learning": { "total": 1318.129153204034, "count": 1, "self": 0.8154609720222652, "children": { "TrainerController._reset_env": { "total": 1.6538130809785798, "count": 1, "self": 1.6538130809785798 }, "TrainerController.advance": { "total": 1315.5938684470602, "count": 63707, "self": 0.7646780640934594, "children": { "env_step": { "total": 799.3870629730518, "count": 63707, "self": 610.819042055693, "children": { "SubprocessEnvManager._take_step": { "total": 188.04416026553372, "count": 63707, "self": 2.518399754422717, "children": { "TorchPolicy.evaluate": { "total": 185.525760511111, "count": 62557, "self": 185.525760511111 } } }, "workers": { "total": 0.523860651825089, "count": 63707, "self": 0.0, "children": { "worker_root": { "total": 1316.373609175207, "count": 63707, "is_parallel": true, "self": 754.72463956906, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015157749876379967, "count": 1, "is_parallel": true, "self": 0.0007382630137726665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007775119738653302, "count": 8, "is_parallel": true, "self": 0.0007775119738653302 } } }, "UnityEnvironment.step": { "total": 0.021499330992810428, "count": 1, "is_parallel": true, "self": 0.00015049200737848878, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014023296535015106, "count": 1, "is_parallel": true, "self": 0.00014023296535015106 }, "communicator.exchange": { "total": 0.02076700300676748, "count": 1, "is_parallel": true, "self": 0.02076700300676748 }, "steps_from_proto": { "total": 0.00044160301331430674, "count": 1, "is_parallel": true, "self": 0.00012207485269755125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003195281606167555, "count": 8, "is_parallel": true, "self": 0.0003195281606167555 } } } } } } }, "UnityEnvironment.step": { "total": 561.6489696061471, "count": 63706, "is_parallel": true, "self": 8.59648663707776, "children": { "UnityEnvironment._generate_step_input": { "total": 6.175521340162959, "count": 63706, "is_parallel": true, "self": 6.175521340162959 }, "communicator.exchange": { "total": 523.7545745486859, "count": 63706, "is_parallel": true, "self": 523.7545745486859 }, "steps_from_proto": { "total": 23.122387080220506, "count": 63706, "is_parallel": true, "self": 5.406074382131919, "children": { "_process_rank_one_or_two_observation": { "total": 17.716312698088586, "count": 509648, "is_parallel": true, "self": 17.716312698088586 } } } } } } } } } } }, "trainer_advance": { "total": 515.442127409915, "count": 63707, "self": 1.4287224989384413, "children": { "process_trajectory": { "total": 83.55797293112846, "count": 63707, "self": 83.37450367916608, "children": { "RLTrainer._checkpoint": { "total": 0.18346925196237862, "count": 2, "self": 0.18346925196237862 } } }, "_update_policy": { "total": 430.4554319798481, "count": 453, "self": 179.48259896133095, "children": { "TorchPPOOptimizer.update": { "total": 250.97283301851712, "count": 22788, "self": 250.97283301851712 } } } } } } }, "trainer_threads": { "total": 4.5902561396360397e-07, "count": 1, "self": 4.5902561396360397e-07 }, "TrainerController._save_models": { "total": 0.0660102449473925, "count": 1, "self": 0.0009948939550668001, "children": { "RLTrainer._checkpoint": { "total": 0.0650153509923257, "count": 1, "self": 0.0650153509923257 } } } } } } }