| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.1341688632965088, | |
| "min": 0.13263465464115143, | |
| "max": 1.3872299194335938, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 4033.65283203125, | |
| "min": 3955.69580078125, | |
| "max": 42083.0078125, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 2999958.0, | |
| "min": 29952.0, | |
| "max": 2999958.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 2999958.0, | |
| "min": 29952.0, | |
| "max": 2999958.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.8524944186210632, | |
| "min": -0.10985395312309265, | |
| "max": 0.9063270688056946, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 261.7157897949219, | |
| "min": -26.364948272705078, | |
| "max": 276.42974853515625, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.012428520247340202, | |
| "min": -0.02336515486240387, | |
| "max": 0.8881713151931763, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 3.8155558109283447, | |
| "min": -6.892720699310303, | |
| "max": 213.16111755371094, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06472630039068117, | |
| "min": 0.06252626269062082, | |
| "max": 0.07702694473929982, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9061682054695364, | |
| "min": 0.5132823468026392, | |
| "max": 1.0936694837000687, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.0154032837772753, | |
| "min": 0.00036945041838324136, | |
| "max": 0.021864434819524593, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.2156459728818542, | |
| "min": 0.004433405020598896, | |
| "max": 0.23363027764043734, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 1.5772494742833342e-06, | |
| "min": 1.5772494742833342e-06, | |
| "max": 0.00029838354339596195, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 2.208149263996668e-05, | |
| "min": 2.208149263996668e-05, | |
| "max": 0.0039825916724695, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10052571666666668, | |
| "min": 0.10052571666666668, | |
| "max": 0.19946118095238097, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4073600333333336, | |
| "min": 1.3897045333333333, | |
| "max": 2.8275305, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 6.251909500000004e-05, | |
| "min": 6.251909500000004e-05, | |
| "max": 0.009946171977142856, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0008752673300000005, | |
| "min": 0.0008752673300000005, | |
| "max": 0.13277029695, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.008665002882480621, | |
| "min": 0.008133871480822563, | |
| "max": 0.6720296740531921, | |
| "count": 100 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1213100403547287, | |
| "min": 0.1168643906712532, | |
| "max": 4.704207897186279, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 202.43243243243242, | |
| "min": 192.05369127516778, | |
| "max": 999.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 29960.0, | |
| "min": 15984.0, | |
| "max": 33179.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.7964093855163394, | |
| "min": -1.0000000521540642, | |
| "max": 1.7964093855163394, | |
| "count": 100 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 267.6649984419346, | |
| "min": -32.000001668930054, | |
| "max": 267.6649984419346, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.7964093855163394, | |
| "min": -1.0000000521540642, | |
| "max": 1.7964093855163394, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 267.6649984419346, | |
| "min": -32.000001668930054, | |
| "max": 267.6649984419346, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.018090883511526434, | |
| "min": 0.01724788235937799, | |
| "max": 15.016267117112875, | |
| "count": 100 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.695541643217439, | |
| "min": 2.4515712619468104, | |
| "max": 240.260273873806, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 100 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1726864333", | |
| "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", | |
| "command_line_arguments": "/home/smitsis/deep_rl/unit5/.venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", | |
| "mlagents_version": "1.1.0.dev0", | |
| "mlagents_envs_version": "1.1.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.4.1+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1726868382" | |
| }, | |
| "total": 4049.3710773970015, | |
| "count": 1, | |
| "self": 0.5895341570030723, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.03725820699764881, | |
| "count": 1, | |
| "self": 0.03725820699764881 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 4048.744285033001, | |
| "count": 1, | |
| "self": 3.717256762243778, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.4224397639991366, | |
| "count": 1, | |
| "self": 3.4224397639991366 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 4041.477001824758, | |
| "count": 195656, | |
| "self": 3.3308607920771465, | |
| "children": { | |
| "env_step": { | |
| "total": 2328.007386639303, | |
| "count": 195656, | |
| "self": 2055.21509451999, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 270.5359504977714, | |
| "count": 195656, | |
| "self": 10.361718275496969, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 260.17423222227444, | |
| "count": 187558, | |
| "self": 260.17423222227444 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 2.256341621541651, | |
| "count": 195656, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 4043.7644807621546, | |
| "count": 195656, | |
| "is_parallel": true, | |
| "self": 2240.803112125108, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0027552920000744052, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007699239940848202, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001985368005989585, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001985368005989585 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.030666878999909386, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0002245820032840129, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00014396199912880547, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00014396199912880547 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.029428026999084977, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.029428026999084977 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0008703079984115902, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00020219699581502937, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0006681110025965609, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0006681110025965609 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1802.9613686370467, | |
| "count": 195655, | |
| "is_parallel": true, | |
| "self": 36.88238994132553, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 34.78763833605626, | |
| "count": 195655, | |
| "is_parallel": true, | |
| "self": 34.78763833605626 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1616.0866041508634, | |
| "count": 195655, | |
| "is_parallel": true, | |
| "self": 1616.0866041508634 | |
| }, | |
| "steps_from_proto": { | |
| "total": 115.20473620880148, | |
| "count": 195655, | |
| "is_parallel": true, | |
| "self": 28.329421952494158, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 86.87531425630732, | |
| "count": 1565240, | |
| "is_parallel": true, | |
| "self": 86.87531425630732 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 1710.138754393378, | |
| "count": 195656, | |
| "self": 7.325309896543331, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 267.4758459489276, | |
| "count": 195656, | |
| "self": 266.97439568792106, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.5014502610065392, | |
| "count": 6, | |
| "self": 0.5014502610065392 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 1435.337598547907, | |
| "count": 1395, | |
| "self": 682.9063918591346, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 752.4312066887724, | |
| "count": 68319, | |
| "self": 752.4312066887724 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.700008038431406e-07, | |
| "count": 1, | |
| "self": 8.700008038431406e-07 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.12758581199886976, | |
| "count": 1, | |
| "self": 0.011729711997759296, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.11585610000111046, | |
| "count": 1, | |
| "self": 0.11585610000111046 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |