{ "name": "root", "gauges": { "PushBlock.Policy.Entropy.mean": { "value": 0.08119317889213562, "min": 0.07939919084310532, "max": 1.873086929321289, "count": 150 }, "PushBlock.Policy.Entropy.sum": { "value": 4879.38525390625, "min": 4761.41064453125, "max": 113643.9296875, "count": 150 }, "PushBlock.Step.mean": { "value": 8999996.0, "min": 59968.0, "max": 8999996.0, "count": 150 }, "PushBlock.Step.sum": { "value": 8999996.0, "min": 59968.0, "max": 8999996.0, "count": 150 }, "PushBlock.Policy.ExtrinsicValueEstimate.mean": { "value": 4.547738552093506, "min": -0.09086691588163376, "max": 4.561385154724121, "count": 150 }, "PushBlock.Policy.ExtrinsicValueEstimate.sum": { "value": 14671.00390625, "min": -87.32310485839844, "max": 15052.5703125, "count": 150 }, "PushBlock.Losses.PolicyLoss.mean": { "value": 0.06880345430302745, "min": 0.06433126581070045, "max": 0.07543855404043733, "count": 150 }, "PushBlock.Losses.PolicyLoss.sum": { "value": 1.9953001747877959, "min": 0.988056154771281, "max": 2.1877180671726824, "count": 150 }, "PushBlock.Losses.ValueLoss.mean": { "value": 0.030789223338855996, "min": 3.065231205960214e-05, "max": 0.3599788421957658, "count": 150 }, "PushBlock.Losses.ValueLoss.sum": { "value": 0.8928874768268239, "min": 0.00045978468089403216, "max": 10.439386423677208, "count": 150 }, "PushBlock.Policy.LearningRate.mean": { "value": 9.709226648980825e-07, "min": 9.709226648980825e-07, "max": 0.0002989888003370666, "count": 150 }, "PushBlock.Policy.LearningRate.sum": { "value": 2.815675728204439e-05, "min": 2.815675728204439e-05, "max": 0.008439436620187821, "count": 150 }, "PushBlock.Policy.Epsilon.mean": { "value": 0.10032360766283527, "min": 0.10032360766283527, "max": 0.19966293333333332, "count": 150 }, "PushBlock.Policy.Epsilon.sum": { "value": 2.909384622222223, "min": 2.7952810666666665, "max": 5.713145511111111, "count": 150 }, "PushBlock.Policy.Beta.mean": { "value": 4.2328405517241326e-05, "min": 4.2328405517241326e-05, "max": 0.00996632704, "count": 150 }, "PushBlock.Policy.Beta.sum": { "value": 0.0012275237599999984, "min": 0.0012275237599999984, "max": 0.28132323656, "count": 150 }, "PushBlock.Environment.EpisodeLength.mean": { "value": 17.56733167082294, "min": 17.40615191462649, "max": 999.0, "count": 150 }, "PushBlock.Environment.EpisodeLength.sum": { "value": 56356.0, "min": 31968.0, "max": 66918.0, "count": 150 }, "PushBlock.Environment.CumulativeReward.mean": { "value": 4.98183390430112, "min": -1.0000000447034836, "max": 4.981994837190435, "count": 150 }, "PushBlock.Environment.CumulativeReward.sum": { "value": 15981.723164997995, "min": -64.00000286102295, "max": 16390.480550043285, "count": 150 }, "PushBlock.Policy.ExtrinsicReward.mean": { "value": 4.98183390430112, "min": -1.0000000447034836, "max": 4.981994837190435, "count": 150 }, "PushBlock.Policy.ExtrinsicReward.sum": { "value": 15981.723164997995, "min": -64.00000286102295, "max": 16390.480550043285, "count": 150 }, "PushBlock.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 150 }, "PushBlock.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 150 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1661064711", "python_version": "3.9.9 | packaged by conda-forge | (main, Dec 20 2021, 02:41:03) \n[GCC 9.4.0]", "command_line_arguments": "/home/laplace/mambaforge/envs/python399/bin/mlagents-learn ./config/ppo/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training 2 --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+cu113", "numpy_version": "1.23.1", "end_time_seconds": "1661076514" }, "total": 11802.912650554998, "count": 1, "self": 0.9893433839970385, "children": { "run_training.setup": { "total": 0.05318127400096273, "count": 1, "self": 0.05318127400096273 }, "TrainerController.start_learning": { "total": 11801.870125897, "count": 1, "self": 11.150327124003525, "children": { "TrainerController._reset_env": { "total": 8.829471929999272, "count": 1, "self": 8.829471929999272 }, "TrainerController.advance": { "total": 11781.734373301992, "count": 531839, "self": 9.544983413819864, "children": { "env_step": { "total": 6374.2015644643325, "count": 531839, "self": 5328.16922110015, "children": { "SubprocessEnvManager._take_step": { "total": 1040.2436070144067, "count": 531839, "self": 18.588477530262026, "children": { "TorchPolicy.evaluate": { "total": 1021.6551294841447, "count": 281261, "self": 547.4066510602388, "children": { "TorchPolicy.sample_actions": { "total": 474.2484784239059, "count": 281261, "self": 474.2484784239059 } } } } }, "workers": { "total": 5.788736349775718, "count": 531839, "self": 0.0, "children": { "worker_root": { "total": 11777.842286660401, "count": 531839, "is_parallel": true, "self": 7068.761654240359, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002291035998496227, "count": 1, "is_parallel": true, "self": 0.0006391450006049126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016518909978913143, "count": 4, "is_parallel": true, "self": 0.0016518909978913143 } } }, "UnityEnvironment.step": { "total": 0.045522884000092745, "count": 1, "is_parallel": true, "self": 0.00025612600074964575, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023558699831482954, "count": 1, "is_parallel": true, "self": 0.00023558699831482954 }, "communicator.exchange": { "total": 0.04411055800301256, "count": 1, "is_parallel": true, "self": 0.04411055800301256 }, "steps_from_proto": { "total": 0.000920612998015713, "count": 1, "is_parallel": true, "self": 0.00022102899674791843, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006995840012677945, "count": 4, "is_parallel": true, "self": 0.0006995840012677945 } } } } } } }, "UnityEnvironment.step": { "total": 4709.080632420042, "count": 531838, "is_parallel": true, "self": 113.76486024145925, "children": { "UnityEnvironment._generate_step_input": { "total": 79.52430546835603, "count": 531838, "is_parallel": true, "self": 79.52430546835603 }, "communicator.exchange": { "total": 4204.048733611598, "count": 531838, "is_parallel": true, "self": 4204.048733611598 }, "steps_from_proto": { "total": 311.7427330986284, "count": 531838, "is_parallel": true, "self": 81.71223001655017, "children": { "_process_rank_one_or_two_observation": { "total": 230.0305030820782, "count": 2127352, "is_parallel": true, "self": 230.0305030820782 } } } } } } } } } } }, "trainer_advance": { "total": 5397.987825423839, "count": 531839, "self": 15.22669144142128, "children": { "process_trajectory": { "total": 1791.3779854763234, "count": 531839, "self": 1788.9837122013414, "children": { "RLTrainer._checkpoint": { "total": 2.3942732749819697, "count": 18, "self": 2.3942732749819697 } } }, "_update_policy": { "total": 3591.3831485060946, "count": 4315, "self": 740.3270784520719, "children": { "TorchPPOOptimizer.update": { "total": 2851.0560700540227, "count": 208941, "self": 2851.0560700540227 } } } } } } }, "trainer_threads": { "total": 7.160051609389484e-07, "count": 1, "self": 7.160051609389484e-07 }, "TrainerController._save_models": { "total": 0.15595282499998575, "count": 1, "self": 0.03610342300089542, "children": { "RLTrainer._checkpoint": { "total": 0.11984940199909033, "count": 1, "self": 0.11984940199909033 } } } } } } }