{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.466756135225296, "min": 0.4416283369064331, "max": 1.4400897026062012, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13920.53515625, "min": 13347.7744140625, "max": 43686.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29952.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3556886315345764, "min": -0.11244145780801773, "max": 0.3614807724952698, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 92.83473205566406, "min": -26.64862632751465, "max": 93.26203918457031, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005279551260173321, "min": -0.04659565910696983, "max": 0.3772234320640564, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3779628276824951, "min": -11.881893157958984, "max": 89.4019546508789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06880583016997359, "min": 0.06480895658970177, "max": 0.07286502115128862, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9632816223796302, "min": 0.5097002897832419, "max": 1.0615522721491288, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01025341187293331, "min": 0.00026736207331906457, "max": 0.011115400992589546, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14354776622106633, "min": 0.003208344879828775, "max": 0.15561561389625364, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.524654634671427e-06, "min": 7.524654634671427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010534516488539997, "min": 0.00010534516488539997, "max": 0.0032526647157785, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250818571428573, "min": 0.10250818571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351146000000001, "min": 1.3886848, "max": 2.4428108, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026056775285714285, "min": 0.00026056775285714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00364794854, "min": 0.00364794854, "max": 0.10844372784999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009841195307672024, "min": 0.009736060164868832, "max": 0.4915636479854584, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13777673244476318, "min": 0.1363048404455185, "max": 3.440945625305176, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 499.6271186440678, "min": 499.6271186440678, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29478.0, "min": 15984.0, "max": 32971.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2630338714284413, "min": -1.0000000521540642, "max": 1.2630338714284413, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 74.51899841427803, "min": -31.997201651334763, "max": 74.51899841427803, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2630338714284413, "min": -1.0000000521540642, "max": 1.2630338714284413, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 74.51899841427803, "min": -31.997201651334763, "max": 74.51899841427803, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05167203982137696, "min": 0.05167203982137696, "max": 9.293166941031814, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0486503494612407, "min": 2.914018386567477, "max": 148.69067105650902, "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": "1703601193", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703603597" }, "total": 2403.9784688259997, "count": 1, "self": 0.5320574569996097, "children": { "run_training.setup": { "total": 0.05074359800005368, "count": 1, "self": 0.05074359800005368 }, "TrainerController.start_learning": { "total": 2403.3956677710003, "count": 1, "self": 1.5811988540067432, "children": { "TrainerController._reset_env": { "total": 2.231394388999888, "count": 1, "self": 2.231394388999888 }, "TrainerController.advance": { "total": 2399.4815790769935, "count": 63450, "self": 1.698070038996775, "children": { "env_step": { "total": 1701.0162385180104, "count": 63450, "self": 1550.160612279041, "children": { "SubprocessEnvManager._take_step": { "total": 149.83871081398024, "count": 63450, "self": 5.43545368902187, "children": { "TorchPolicy.evaluate": { "total": 144.40325712495837, "count": 62557, "self": 144.40325712495837 } } }, "workers": { "total": 1.0169154249890653, "count": 63450, "self": 0.0, "children": { "worker_root": { "total": 2397.5267114609683, "count": 63450, "is_parallel": true, "self": 987.1121968739039, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018369990000337566, "count": 1, "is_parallel": true, "self": 0.0005629050003790326, "children": { "_process_rank_one_or_two_observation": { "total": 0.001274093999654724, "count": 8, "is_parallel": true, "self": 0.001274093999654724 } } }, "UnityEnvironment.step": { "total": 0.05867001800015714, "count": 1, "is_parallel": true, "self": 0.0006931730001724645, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005454970000755566, "count": 1, "is_parallel": true, "self": 0.0005454970000755566 }, "communicator.exchange": { "total": 0.055441297000015766, "count": 1, "is_parallel": true, "self": 0.055441297000015766 }, "steps_from_proto": { "total": 0.0019900509998933558, "count": 1, "is_parallel": true, "self": 0.00041158799967888626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015784630002144695, "count": 8, "is_parallel": true, "self": 0.0015784630002144695 } } } } } } }, "UnityEnvironment.step": { "total": 1410.4145145870643, "count": 63449, "is_parallel": true, "self": 40.00806914799068, "children": { "UnityEnvironment._generate_step_input": { "total": 28.414284759024895, "count": 63449, "is_parallel": true, "self": 28.414284759024895 }, "communicator.exchange": { "total": 1224.0449138999918, "count": 63449, "is_parallel": true, "self": 1224.0449138999918 }, "steps_from_proto": { "total": 117.94724678005696, "count": 63449, "is_parallel": true, "self": 24.52075093909002, "children": { "_process_rank_one_or_two_observation": { "total": 93.42649584096694, "count": 507592, "is_parallel": true, "self": 93.42649584096694 } } } } } } } } } } }, "trainer_advance": { "total": 696.7672705199861, "count": 63450, "self": 3.0378207969974937, "children": { "process_trajectory": { "total": 143.62046141199016, "count": 63450, "self": 143.39854130798994, "children": { "RLTrainer._checkpoint": { "total": 0.221920104000219, "count": 2, "self": 0.221920104000219 } } }, "_update_policy": { "total": 550.1089883109985, "count": 448, "self": 329.0852884029837, "children": { "TorchPPOOptimizer.update": { "total": 221.0236999080148, "count": 22809, "self": 221.0236999080148 } } } } } } }, "trainer_threads": { "total": 1.6159997358045075e-06, "count": 1, "self": 1.6159997358045075e-06 }, "TrainerController._save_models": { "total": 0.10149383500038311, "count": 1, "self": 0.0015524300006291014, "children": { "RLTrainer._checkpoint": { "total": 0.09994140499975401, "count": 1, "self": 0.09994140499975401 } } } } } } }