{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38326001167297363, "min": 0.3646904528141022, "max": 1.3517982959747314, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11528.4609375, "min": 10818.177734375, "max": 41008.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5532466769218445, "min": -0.07840621471405029, "max": 0.5565416812896729, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.80258178710938, "min": -18.97430419921875, "max": 153.80258178710938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01744486391544342, "min": -0.026949116960167885, "max": 0.54945969581604, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.849672317504883, "min": -7.276261329650879, "max": 130.22195434570312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0671634659485703, "min": 0.06508727559481658, "max": 0.07482523151362935, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9402885232799841, "min": 0.5064664202211719, "max": 1.1223784727044404, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01649443761700587, "min": 0.0007308875295051967, "max": 0.01649443761700587, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23092212663808218, "min": 0.009501537883567557, "max": 0.23092212663808218, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.67943315450714e-06, "min": 7.67943315450714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010751206416309996, "min": 0.00010751206416309996, "max": 0.0037587856470715003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255977857142855, "min": 0.10255977857142855, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358368999999997, "min": 1.3886848, "max": 2.6529285000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026572187928571424, "min": 0.00026572187928571424, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037201063099999996, "min": 0.0037201063099999996, "max": 0.12530755715, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01760769449174404, "min": 0.017308497801423073, "max": 0.7073035836219788, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24650773406028748, "min": 0.24231895804405212, "max": 4.951125144958496, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 321.39772727272725, "min": 321.39772727272725, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28283.0, "min": 15984.0, "max": 33803.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6786022513088854, "min": -1.0000000521540642, "max": 1.6786022513088854, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.71699811518192, "min": -29.64100157469511, "max": 147.71699811518192, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6786022513088854, "min": -1.0000000521540642, "max": 1.6786022513088854, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.71699811518192, "min": -29.64100157469511, "max": 147.71699811518192, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.058175617599441794, "min": 0.058175617599441794, "max": 14.939263613894582, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.119454348750878, "min": 5.119454348750878, "max": 239.0282178223133, "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": "1664325614", "python_version": "3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\erich\\miniconda3\\envs\\hf-ml-agents\\Scripts\\mlagents-learn .\\config\\ppo\\PyramidsRND.yaml --env .\\trained-envs-executables\\windows\\Pyramids\\ --run-id first training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.12.1", "numpy_version": "1.23.1", "end_time_seconds": "1664327737" }, "total": 2123.5308058, "count": 1, "self": 0.7082409999998163, "children": { "run_training.setup": { "total": 0.13103909999999974, "count": 1, "self": 0.13103909999999974 }, "TrainerController.start_learning": { "total": 2122.6915257, "count": 1, "self": 1.52914479999572, "children": { "TrainerController._reset_env": { "total": 8.6770876, "count": 1, "self": 8.6770876 }, "TrainerController.advance": { "total": 2112.352217500005, "count": 63875, "self": 1.3369779000145172, "children": { "env_step": { "total": 1023.3772189999993, "count": 63875, "self": 830.224870199926, "children": { "SubprocessEnvManager._take_step": { "total": 192.16534390005074, "count": 63875, "self": 5.35020100007813, "children": { "TorchPolicy.evaluate": { "total": 186.8151428999726, "count": 62577, "self": 80.90848829997962, "children": { "TorchPolicy.sample_actions": { "total": 105.90665459999299, "count": 62577, "self": 105.90665459999299 } } } } }, "workers": { "total": 0.9870049000225123, "count": 63875, "self": 0.0, "children": { "worker_root": { "total": 2112.9039863999556, "count": 63875, "is_parallel": true, "self": 1392.6909349999332, "children": { "steps_from_proto": { "total": 0.001105100000000192, "count": 1, "is_parallel": true, "self": 0.0002996999999993477, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008054000000008443, "count": 8, "is_parallel": true, "self": 0.0008054000000008443 } } }, "UnityEnvironment.step": { "total": 720.2119463000224, "count": 63875, "is_parallel": true, "self": 19.97030120003717, "children": { "UnityEnvironment._generate_step_input": { "total": 17.104151000009637, "count": 63875, "is_parallel": true, "self": 17.104151000009637 }, "communicator.exchange": { "total": 626.5370090999984, "count": 63875, "is_parallel": true, "self": 626.5370090999984 }, "steps_from_proto": { "total": 56.60048499997715, "count": 63875, "is_parallel": true, "self": 14.52378619997161, "children": { "_process_rank_one_or_two_observation": { "total": 42.07669880000554, "count": 511000, "is_parallel": true, "self": 42.07669880000554 } } } } } } } } } } }, "trainer_advance": { "total": 1087.6380205999913, "count": 63875, "self": 3.020272999999179, "children": { "process_trajectory": { "total": 209.0864455999906, "count": 63875, "self": 208.77805729999045, "children": { "RLTrainer._checkpoint": { "total": 0.3083883000001606, "count": 2, "self": 0.3083883000001606 } } }, "_update_policy": { "total": 875.5313020000015, "count": 458, "self": 230.43345849998923, "children": { "TorchPPOOptimizer.update": { "total": 645.0978435000122, "count": 22767, "self": 645.0978435000122 } } } } } } }, "trainer_threads": { "total": 7.999997251317836e-07, "count": 1, "self": 7.999997251317836e-07 }, "TrainerController._save_models": { "total": 0.13307499999973516, "count": 1, "self": 0.006068600000162405, "children": { "RLTrainer._checkpoint": { "total": 0.12700639999957275, "count": 1, "self": 0.12700639999957275 } } } } } } }