{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5206964015960693, "min": 0.5175266861915588, "max": 1.5165607929229736, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15454.26953125, "min": 15440.57421875, "max": 46006.38671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6127291321754456, "min": -0.07732558995485306, "max": 0.6127291321754456, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.88778686523438, "min": -18.738847732543945, "max": 167.88778686523438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.009591849520802498, "min": -0.009591849520802498, "max": 0.2703345715999603, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.628166675567627, "min": -2.628166675567627, "max": 64.88029479980469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06517964712241717, "min": 0.06517964712241717, "max": 0.07271911004611221, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9125150597138404, "min": 0.4829916822420963, "max": 1.0702147424162831, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013607569009886406, "min": 0.0004532406971701017, "max": 0.013674788421970636, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19050596613840967, "min": 0.0036259255773608136, "max": 0.1914470379075889, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.484326076685713e-06, "min": 7.484326076685713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010478056507359998, "min": 0.00010478056507359998, "max": 0.0035097095300968997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249474285714287, "min": 0.10249474285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349264000000002, "min": 1.3691136000000002, "max": 2.5699031000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025922481142857137, "min": 0.00025922481142857137, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036291473599999995, "min": 0.0036291473599999995, "max": 0.11701331969000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013575547374784946, "min": 0.013503861613571644, "max": 0.4338116943836212, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1900576651096344, "min": 0.18905405700206757, "max": 3.036681890487671, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.02197802197804, "min": 332.1808510638298, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30760.0, "min": 15984.0, "max": 35225.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.639995590179831, "min": -1.0000000521540642, "max": 1.6465404135115602, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 149.23959870636463, "min": -32.000001668930054, "max": 154.77479887008667, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.639995590179831, "min": -1.0000000521540642, "max": 1.6465404135115602, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 149.23959870636463, "min": -32.000001668930054, "max": 154.77479887008667, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0469639694316896, "min": 0.04626125807439205, "max": 8.522619388066232, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.273721218283754, "min": 4.273721218283754, "max": 136.36191020905972, "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": "1709925284", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709927738" }, "total": 2454.278896996, "count": 1, "self": 0.5265056619996358, "children": { "run_training.setup": { "total": 0.050053407000177685, "count": 1, "self": 0.050053407000177685 }, "TrainerController.start_learning": { "total": 2453.7023379270004, "count": 1, "self": 1.6562968759862997, "children": { "TrainerController._reset_env": { "total": 2.1853611569999885, "count": 1, "self": 2.1853611569999885 }, "TrainerController.advance": { "total": 2449.774257295014, "count": 63751, "self": 1.7858668069334271, "children": { "env_step": { "total": 1763.6431406520169, "count": 63751, "self": 1612.9067589421356, "children": { "SubprocessEnvManager._take_step": { "total": 149.67619292590462, "count": 63751, "self": 5.404752591888155, "children": { "TorchPolicy.evaluate": { "total": 144.27144033401646, "count": 62562, "self": 144.27144033401646 } } }, "workers": { "total": 1.0601887839766277, "count": 63751, "self": 0.0, "children": { "worker_root": { "total": 2447.638759193072, "count": 63751, "is_parallel": true, "self": 976.3586288260863, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022039659997972194, "count": 1, "is_parallel": true, "self": 0.0006456640003307257, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015583019994664937, "count": 8, "is_parallel": true, "self": 0.0015583019994664937 } } }, "UnityEnvironment.step": { "total": 0.04636226599996007, "count": 1, "is_parallel": true, "self": 0.000625964999471762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004694200001722493, "count": 1, "is_parallel": true, "self": 0.0004694200001722493 }, "communicator.exchange": { "total": 0.04361736100008784, "count": 1, "is_parallel": true, "self": 0.04361736100008784 }, "steps_from_proto": { "total": 0.0016495200002282218, "count": 1, "is_parallel": true, "self": 0.00035618599940789863, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012933340008203231, "count": 8, "is_parallel": true, "self": 0.0012933340008203231 } } } } } } }, "UnityEnvironment.step": { "total": 1471.2801303669858, "count": 63750, "is_parallel": true, "self": 39.50275399500788, "children": { "UnityEnvironment._generate_step_input": { "total": 25.34149342208684, "count": 63750, "is_parallel": true, "self": 25.34149342208684 }, "communicator.exchange": { "total": 1295.8040629879765, "count": 63750, "is_parallel": true, "self": 1295.8040629879765 }, "steps_from_proto": { "total": 110.63181996191452, "count": 63750, "is_parallel": true, "self": 23.03978924167177, "children": { "_process_rank_one_or_two_observation": { "total": 87.59203072024275, "count": 510000, "is_parallel": true, "self": 87.59203072024275 } } } } } } } } } } }, "trainer_advance": { "total": 684.3452498360639, "count": 63751, "self": 3.3571398900012355, "children": { "process_trajectory": { "total": 137.97709261306272, "count": 63751, "self": 137.76281429606252, "children": { "RLTrainer._checkpoint": { "total": 0.2142783170002076, "count": 2, "self": 0.2142783170002076 } } }, "_update_policy": { "total": 543.0110173329999, "count": 445, "self": 318.58118542295006, "children": { "TorchPPOOptimizer.update": { "total": 224.42983191004987, "count": 22851, "self": 224.42983191004987 } } } } } } }, "trainer_threads": { "total": 8.309998520417139e-07, "count": 1, "self": 8.309998520417139e-07 }, "TrainerController._save_models": { "total": 0.08642176800003654, "count": 1, "self": 0.0013762219996351632, "children": { "RLTrainer._checkpoint": { "total": 0.08504554600040137, "count": 1, "self": 0.08504554600040137 } } } } } } }