{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41511183977127075, "min": 0.379581481218338, "max": 0.6043116450309753, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 4283.9541015625, "min": 3845.06591796875, "max": 6246.1650390625, "count": 50 }, "Pyramids.Step.mean": { "value": 1499962.0, "min": 1009976.0, "max": 1499962.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499962.0, "min": 1009976.0, "max": 1499962.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4872138202190399, "min": 0.05979938432574272, "max": 0.5726072788238525, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 45.798099517822266, "min": 4.7839508056640625, "max": 53.252479553222656, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03181224316358566, "min": -0.03181224316358566, "max": 0.08744346350431442, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.9903507232666016, "min": -2.9903507232666016, "max": 8.132242202758789, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06694401380761215, "min": 0.0607478265146104, "max": 0.0778923243827497, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3347200690380608, "min": 0.18451486450309554, "max": 0.38359445321839303, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018834684311877938, "min": 0.005653721174288269, "max": 0.018834684311877938, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.09417342155938968, "min": 0.022614884697153077, "max": 0.09417342155938968, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.854597048799994e-07, "min": 8.854597048799994e-07, "max": 9.87590004136889e-05, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.427298524399997e-06, "min": 4.427298524399997e-06, "max": 0.00048500073833319994, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10029512, "min": 0.10029512, "max": 0.13291964444444446, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5014756, "min": 0.39875893333333334, "max": 0.6616668000000001, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 3.948248799999999e-05, "min": 3.948248799999999e-05, "max": 0.0032986724800000006, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.00019741243999999992, "min": 0.00019741243999999992, "max": 0.01620051332, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009386932477355003, "min": 0.008871779777109623, "max": 0.021980872377753258, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.04693466052412987, "min": 0.03788800165057182, "max": 0.08285048604011536, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.6551724137931, "min": 322.27272727272725, "max": 789.2, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 10198.0, "min": 1897.0, "max": 13663.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5103586097729618, "min": 0.24627997279167174, "max": 1.6636071311576026, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 43.80039968341589, "min": 2.4627997279167175, "max": 54.72899912297726, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5103586097729618, "min": 0.24627997279167174, "max": 1.6636071311576026, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 43.80039968341589, "min": 2.4627997279167175, "max": 54.72899912297726, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03490569133407854, "min": 0.03359096942469478, "max": 0.13430134480586275, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 1.0122650486882776, "min": 0.33041048038285226, "max": 2.148821516893804, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700669876", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700671097" }, "total": 1220.7294129299999, "count": 1, "self": 0.47803199099871563, "children": { "run_training.setup": { "total": 0.0446211200005564, "count": 1, "self": 0.0446211200005564 }, "TrainerController.start_learning": { "total": 1220.2067598190006, "count": 1, "self": 0.7437315478828168, "children": { "TrainerController._reset_env": { "total": 4.134272136000618, "count": 1, "self": 4.134272136000618 }, "TrainerController.advance": { "total": 1215.2507424591176, "count": 32203, "self": 0.7491293730899997, "children": { "env_step": { "total": 883.3887531708888, "count": 32203, "self": 813.4666496741065, "children": { "SubprocessEnvManager._take_step": { "total": 69.4743050678926, "count": 32203, "self": 2.4017155919837023, "children": { "TorchPolicy.evaluate": { "total": 67.0725894759089, "count": 31319, "self": 67.0725894759089 } } }, "workers": { "total": 0.44779842888965504, "count": 32203, "self": 0.0, "children": { "worker_root": { "total": 1217.540503331922, "count": 32203, "is_parallel": true, "self": 468.9795350568611, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019273340003564954, "count": 1, "is_parallel": true, "self": 0.0007131560014386196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012141779989178758, "count": 8, "is_parallel": true, "self": 0.0012141779989178758 } } }, "UnityEnvironment.step": { "total": 0.050393460000123014, "count": 1, "is_parallel": true, "self": 0.0005697900005543488, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004963479996149545, "count": 1, "is_parallel": true, "self": 0.0004963479996149545 }, "communicator.exchange": { "total": 0.047540343000036955, "count": 1, "is_parallel": true, "self": 0.047540343000036955 }, "steps_from_proto": { "total": 0.0017869789999167551, "count": 1, "is_parallel": true, "self": 0.0003905709991158801, "children": { "_process_rank_one_or_two_observation": { "total": 0.001396408000800875, "count": 8, "is_parallel": true, "self": 0.001396408000800875 } } } } } } }, "UnityEnvironment.step": { "total": 748.560968275061, "count": 32202, "is_parallel": true, "self": 17.396085019255224, "children": { "UnityEnvironment._generate_step_input": { "total": 12.869784766995508, "count": 32202, "is_parallel": true, "self": 12.869784766995508 }, "communicator.exchange": { "total": 666.1160614319333, "count": 32202, "is_parallel": true, "self": 666.1160614319333 }, "steps_from_proto": { "total": 52.17903705687695, "count": 32202, "is_parallel": true, "self": 10.672621504089875, "children": { "_process_rank_one_or_two_observation": { "total": 41.506415552787075, "count": 257616, "is_parallel": true, "self": 41.506415552787075 } } } } } } } } } } }, "trainer_advance": { "total": 331.11285991513887, "count": 32203, "self": 1.4475519231664293, "children": { "process_trajectory": { "total": 67.92937983497086, "count": 32203, "self": 67.83041549197151, "children": { "RLTrainer._checkpoint": { "total": 0.09896434299935208, "count": 1, "self": 0.09896434299935208 } } }, "_update_policy": { "total": 261.7359281570016, "count": 235, "self": 155.89730558705105, "children": { "TorchPPOOptimizer.update": { "total": 105.83862256995053, "count": 11376, "self": 105.83862256995053 } } } } } } }, "trainer_threads": { "total": 1.264999809791334e-06, "count": 1, "self": 1.264999809791334e-06 }, "TrainerController._save_models": { "total": 0.07801241099969047, "count": 1, "self": 0.0017386769995937357, "children": { "RLTrainer._checkpoint": { "total": 0.07627373400009674, "count": 1, "self": 0.07627373400009674 } } } } } } }