{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4558856189250946, "min": 0.44927892088890076, "max": 1.3914389610290527, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13676.568359375, "min": 13413.671875, "max": 42210.69140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989949.0, "min": 29952.0, "max": 989949.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.32758575677871704, "min": -0.10990159958600998, "max": 0.4448711574077606, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 86.81022644042969, "min": -26.596187591552734, "max": 117.44598388671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.294693261384964, "min": -0.08406741917133331, "max": 0.34765201807022095, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 78.09371185302734, "min": -21.605327606201172, "max": 83.78413391113281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06753018361803911, "min": 0.06624631034769575, "max": 0.07205640759626951, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9454225706525475, "min": 0.48882595184607025, "max": 1.0249274508581339, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.025300355013834108, "min": 0.0002137848854233848, "max": 0.025300355013834108, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3542049701936775, "min": 0.002992988395927387, "max": 0.3542049701936775, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.332526127285717e-06, "min": 7.332526127285717e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010265536578200004, "min": 0.00010265536578200004, "max": 0.003632151189283, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244414285714287, "min": 0.10244414285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342180000000002, "min": 1.3886848, "max": 2.610717, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002541698714285715, "min": 0.0002541698714285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003558378200000001, "min": 0.003558378200000001, "max": 0.12109062829999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014893299899995327, "min": 0.014893299899995327, "max": 0.5463327765464783, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20850619673728943, "min": 0.20850619673728943, "max": 3.8243296146392822, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 486.3, "min": 439.3181818181818, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29178.0, "min": 15984.0, "max": 34053.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.280296641215682, "min": -1.0000000521540642, "max": 1.4687343135253708, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 76.81779847294092, "min": -29.478001683950424, "max": 98.40519900619984, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.280296641215682, "min": -1.0000000521540642, "max": 1.4687343135253708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 76.81779847294092, "min": -29.478001683950424, "max": 98.40519900619984, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0752396803892528, "min": 0.07366888058868426, "max": 11.002530466765165, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.514380823355168, "min": 4.514380823355168, "max": 176.04048746824265, "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": "1744191074", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/POWERCOM.CO/essam/miniconda3/envs/hf_rl_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1744191751" }, "total": 676.5432036839193, "count": 1, "self": 0.21744636306539178, "children": { "run_training.setup": { "total": 0.009865145897492766, "count": 1, "self": 0.009865145897492766 }, "TrainerController.start_learning": { "total": 676.3158921749564, "count": 1, "self": 0.7267002738080919, "children": { "TrainerController._reset_env": { "total": 1.280196448089555, "count": 1, "self": 1.280196448089555 }, "TrainerController.advance": { "total": 674.2028135070577, "count": 63483, "self": 0.6779708686517552, "children": { "env_step": { "total": 426.99980562587734, "count": 63483, "self": 361.65747827105224, "children": { "SubprocessEnvManager._take_step": { "total": 64.8903000758728, "count": 63483, "self": 2.1216343111591414, "children": { "TorchPolicy.evaluate": { "total": 62.76866576471366, "count": 62566, "self": 62.76866576471366 } } }, "workers": { "total": 0.45202727895230055, "count": 63483, "self": 0.0, "children": { "worker_root": { "total": 674.8742222512374, "count": 63483, "is_parallel": true, "self": 353.2552180583589, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007420639740303159, "count": 1, "is_parallel": true, "self": 0.00021930690854787827, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005227570654824376, "count": 8, "is_parallel": true, "self": 0.0005227570654824376 } } }, "UnityEnvironment.step": { "total": 0.014747812994755805, "count": 1, "is_parallel": true, "self": 0.00015882193110883236, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014024204574525356, "count": 1, "is_parallel": true, "self": 0.00014024204574525356 }, "communicator.exchange": { "total": 0.014017609064467251, "count": 1, "is_parallel": true, "self": 0.014017609064467251 }, "steps_from_proto": { "total": 0.0004311399534344673, "count": 1, "is_parallel": true, "self": 0.00010385783389210701, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003272821195423603, "count": 8, "is_parallel": true, "self": 0.0003272821195423603 } } } } } } }, "UnityEnvironment.step": { "total": 321.6190041928785, "count": 63482, "is_parallel": true, "self": 8.833926510065794, "children": { "UnityEnvironment._generate_step_input": { "total": 5.660387705080211, "count": 63482, "is_parallel": true, "self": 5.660387705080211 }, "communicator.exchange": { "total": 283.2492432567524, "count": 63482, "is_parallel": true, "self": 283.2492432567524 }, "steps_from_proto": { "total": 23.875446720980108, "count": 63482, "is_parallel": true, "self": 5.459083212655969, "children": { "_process_rank_one_or_two_observation": { "total": 18.41636350832414, "count": 507856, "is_parallel": true, "self": 18.41636350832414 } } } } } } } } } } }, "trainer_advance": { "total": 246.52503701252863, "count": 63483, "self": 1.289110086625442, "children": { "process_trajectory": { "total": 49.052704443922266, "count": 63483, "self": 48.42543287598528, "children": { "RLTrainer._checkpoint": { "total": 0.6272715679369867, "count": 2, "self": 0.6272715679369867 } } }, "_update_policy": { "total": 196.18322248198092, "count": 450, "self": 110.24167136626784, "children": { "TorchPPOOptimizer.update": { "total": 85.94155111571308, "count": 22740, "self": 85.94155111571308 } } } } } } }, "trainer_threads": { "total": 1.035979948937893e-06, "count": 1, "self": 1.035979948937893e-06 }, "TrainerController._save_models": { "total": 0.10618091002106667, "count": 1, "self": 0.02696055208798498, "children": { "RLTrainer._checkpoint": { "total": 0.07922035793308169, "count": 1, "self": 0.07922035793308169 } } } } } } }