{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3062904477119446, "min": 0.3062904477119446, "max": 1.483149528503418, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9110.302734375, "min": 9110.302734375, "max": 44992.82421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5400733947753906, "min": -0.07550475746393204, "max": 0.5400733947753906, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.98011779785156, "min": -18.272151947021484, "max": 147.98011779785156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.003848339430987835, "min": -0.019627228379249573, "max": 0.3964598476886749, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.0544450283050537, "min": -5.358233451843262, "max": 95.15036010742188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06650966816925487, "min": 0.06394306989105422, "max": 0.07305806230388605, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9311353543695682, "min": 0.49908176488336714, "max": 1.0958709345582907, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01450072873696973, "min": 0.0018719753073118072, "max": 0.01450072873696973, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20301020231757622, "min": 0.024335678995053494, "max": 0.20301020231757622, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.435876092835712e-06, "min": 7.435876092835712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010410226529969996, "min": 0.00010410226529969996, "max": 0.0036328669890444, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247859285714286, "min": 0.10247859285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347003, "min": 1.3886848, "max": 2.6109556, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002576114264285715, "min": 0.0002576114264285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036065599700000005, "min": 0.0036065599700000005, "max": 0.12111446444, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014619313180446625, "min": 0.014619313180446625, "max": 0.6013157963752747, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20467038452625275, "min": 0.20467038452625275, "max": 4.209210395812988, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.65432098765433, "min": 345.65432098765433, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27998.0, "min": 15984.0, "max": 33745.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6296518288644743, "min": -1.0000000521540642, "max": 1.6296518288644743, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 132.00179813802242, "min": -28.369001679122448, "max": 132.00179813802242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6296518288644743, "min": -1.0000000521540642, "max": 1.6296518288644743, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 132.00179813802242, "min": -28.369001679122448, "max": 132.00179813802242, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05194051695551384, "min": 0.05194051695551384, "max": 12.863659173250198, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.207181873396621, "min": 4.207181873396621, "max": 205.81854677200317, "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": "1684567819", "python_version": "3.8.16 (default, Mar 2 2023, 03:21:46) \n[GCC 11.2.0]", "command_line_arguments": "/home/falguni/anaconda3/envs/huggingface_rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684569519" }, "total": 1699.718100375998, "count": 1, "self": 0.3733704749975004, "children": { "run_training.setup": { "total": 0.014375915001437534, "count": 1, "self": 0.014375915001437534 }, "TrainerController.start_learning": { "total": 1699.330353985999, "count": 1, "self": 1.390591524388583, "children": { "TrainerController._reset_env": { "total": 3.222480217998964, "count": 1, "self": 3.222480217998964 }, "TrainerController.advance": { "total": 1694.6153367436127, "count": 63774, "self": 1.4377805909862218, "children": { "env_step": { "total": 1124.6649653008608, "count": 63774, "self": 1012.4232031156898, "children": { "SubprocessEnvManager._take_step": { "total": 111.30734430408484, "count": 63774, "self": 4.44337560128406, "children": { "TorchPolicy.evaluate": { "total": 106.86396870280078, "count": 62547, "self": 106.86396870280078 } } }, "workers": { "total": 0.9344178810861195, "count": 63774, "self": 0.0, "children": { "worker_root": { "total": 1696.9714827026946, "count": 63774, "is_parallel": true, "self": 785.5506452693044, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015219889974105172, "count": 1, "is_parallel": true, "self": 0.00043795098827104084, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010840380091394763, "count": 8, "is_parallel": true, "self": 0.0010840380091394763 } } }, "UnityEnvironment.step": { "total": 0.037847105999389896, "count": 1, "is_parallel": true, "self": 0.0003049079969059676, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045532100193668157, "count": 1, "is_parallel": true, "self": 0.00045532100193668157 }, "communicator.exchange": { "total": 0.03617012600079761, "count": 1, "is_parallel": true, "self": 0.03617012600079761 }, "steps_from_proto": { "total": 0.0009167509997496381, "count": 1, "is_parallel": true, "self": 0.00020246100393706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007142899958125781, "count": 8, "is_parallel": true, "self": 0.0007142899958125781 } } } } } } }, "UnityEnvironment.step": { "total": 911.4208374333903, "count": 63773, "is_parallel": true, "self": 27.920685563411098, "children": { "UnityEnvironment._generate_step_input": { "total": 17.162768520389363, "count": 63773, "is_parallel": true, "self": 17.162768520389363 }, "communicator.exchange": { "total": 788.635541220272, "count": 63773, "is_parallel": true, "self": 788.635541220272 }, "steps_from_proto": { "total": 77.70184212931781, "count": 63773, "is_parallel": true, "self": 15.308654534077505, "children": { "_process_rank_one_or_two_observation": { "total": 62.393187595240306, "count": 510184, "is_parallel": true, "self": 62.393187595240306 } } } } } } } } } } }, "trainer_advance": { "total": 568.5125908517657, "count": 63774, "self": 2.4510593224331387, "children": { "process_trajectory": { "total": 99.36645908633727, "count": 63774, "self": 99.13517773434069, "children": { "RLTrainer._checkpoint": { "total": 0.23128135199658573, "count": 2, "self": 0.23128135199658573 } } }, "_update_policy": { "total": 466.6950724429953, "count": 455, "self": 292.2432705252504, "children": { "TorchPPOOptimizer.update": { "total": 174.4518019177449, "count": 22803, "self": 174.4518019177449 } } } } } } }, "trainer_threads": { "total": 1.0139992809854448e-06, "count": 1, "self": 1.0139992809854448e-06 }, "TrainerController._save_models": { "total": 0.10194448599941097, "count": 1, "self": 0.0017707339975459035, "children": { "RLTrainer._checkpoint": { "total": 0.10017375200186507, "count": 1, "self": 0.10017375200186507 } } } } } } }