{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31355521082878113, "min": 0.31069883704185486, "max": 1.470126748085022, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9406.65625, "min": 9335.87890625, "max": 44597.765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6625138521194458, "min": -0.08625052869319916, "max": 0.6625138521194458, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 190.80398559570312, "min": -20.786376953125, "max": 190.80398559570312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.023519672453403473, "min": -0.0003497330762911588, "max": 0.4878869354724884, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.773665428161621, "min": -0.09617659449577332, "max": 115.62920379638672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07071380875727516, "min": 0.06527877752501762, "max": 0.07279266869036724, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9899933226018522, "min": 0.5013061369009565, "max": 1.0399303043765635, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0172879818502614, "min": 0.00024956367645216735, "max": 0.018370240206584437, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24203174590365958, "min": 0.0032443277938781754, "max": 0.27555360309876653, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.475647508149998e-06, "min": 7.475647508149998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010465906511409997, "min": 0.00010465906511409997, "max": 0.0033758758747080998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249184999999998, "min": 0.10249184999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348858999999998, "min": 1.3886848, "max": 2.4846014000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025893581499999996, "min": 0.00025893581499999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036251014099999996, "min": 0.0036251014099999996, "max": 0.11254666080999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014173387549817562, "min": 0.013540646992623806, "max": 0.5382587909698486, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19842742383480072, "min": 0.18956905603408813, "max": 3.7678115367889404, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 275.27272727272725, "min": 275.27272727272725, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30280.0, "min": 15984.0, "max": 33357.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6696161978148125, "min": -1.0000000521540642, "max": 1.6931235131387616, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.3273979574442, "min": -31.994001641869545, "max": 185.3273979574442, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6696161978148125, "min": -1.0000000521540642, "max": 1.6931235131387616, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.3273979574442, "min": -31.994001641869545, "max": 185.3273979574442, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03997452010970609, "min": 0.03997452010970609, "max": 11.351814521476626, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.437171732177376, "min": 3.911135181755526, "max": 181.62903234362602, "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": "1736361374", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736363959" }, "total": 2584.4189311669998, "count": 1, "self": 0.53427792399998, "children": { "run_training.setup": { "total": 0.059103026000229875, "count": 1, "self": 0.059103026000229875 }, "TrainerController.start_learning": { "total": 2583.8255502169995, "count": 1, "self": 1.45935314187318, "children": { "TrainerController._reset_env": { "total": 2.49851868199994, "count": 1, "self": 2.49851868199994 }, "TrainerController.advance": { "total": 2579.7792310251266, "count": 64060, "self": 1.5040922263351604, "children": { "env_step": { "total": 1813.65362438097, "count": 64060, "self": 1654.0351420987613, "children": { "SubprocessEnvManager._take_step": { "total": 158.71886761307178, "count": 64060, "self": 4.973839838998629, "children": { "TorchPolicy.evaluate": { "total": 153.74502777407315, "count": 62571, "self": 153.74502777407315 } } }, "workers": { "total": 0.8996146691370086, "count": 64060, "self": 0.0, "children": { "worker_root": { "total": 2578.206185923049, "count": 64060, "is_parallel": true, "self": 1051.2227796260863, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023062710001795494, "count": 1, "is_parallel": true, "self": 0.0007542900007138087, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015519809994657408, "count": 8, "is_parallel": true, "self": 0.0015519809994657408 } } }, "UnityEnvironment.step": { "total": 0.0518640619998223, "count": 1, "is_parallel": true, "self": 0.0007437440003741358, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005223939997449634, "count": 1, "is_parallel": true, "self": 0.0005223939997449634 }, "communicator.exchange": { "total": 0.0485710759999165, "count": 1, "is_parallel": true, "self": 0.0485710759999165 }, "steps_from_proto": { "total": 0.002026847999786696, "count": 1, "is_parallel": true, "self": 0.0004710150001301372, "children": { "_process_rank_one_or_two_observation": { "total": 0.001555832999656559, "count": 8, "is_parallel": true, "self": 0.001555832999656559 } } } } } } }, "UnityEnvironment.step": { "total": 1526.9834062969626, "count": 64059, "is_parallel": true, "self": 36.46983750492063, "children": { "UnityEnvironment._generate_step_input": { "total": 24.21280346103549, "count": 64059, "is_parallel": true, "self": 24.21280346103549 }, "communicator.exchange": { "total": 1358.5405101849965, "count": 64059, "is_parallel": true, "self": 1358.5405101849965 }, "steps_from_proto": { "total": 107.76025514600997, "count": 64059, "is_parallel": true, "self": 22.100596488935025, "children": { "_process_rank_one_or_two_observation": { "total": 85.65965865707494, "count": 512472, "is_parallel": true, "self": 85.65965865707494 } } } } } } } } } } }, "trainer_advance": { "total": 764.6215144178213, "count": 64060, "self": 2.850045881843471, "children": { "process_trajectory": { "total": 144.41269349397044, "count": 64060, "self": 144.1473300929706, "children": { "RLTrainer._checkpoint": { "total": 0.26536340099983136, "count": 2, "self": 0.26536340099983136 } } }, "_update_policy": { "total": 617.3587750420074, "count": 449, "self": 350.48584335497026, "children": { "TorchPPOOptimizer.update": { "total": 266.8729316870372, "count": 22836, "self": 266.8729316870372 } } } } } } }, "trainer_threads": { "total": 9.69999746303074e-07, "count": 1, "self": 9.69999746303074e-07 }, "TrainerController._save_models": { "total": 0.08844639800008736, "count": 1, "self": 0.00160165000033885, "children": { "RLTrainer._checkpoint": { "total": 0.0868447479997485, "count": 1, "self": 0.0868447479997485 } } } } } } }