{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.256830632686615, "min": 0.256830632686615, "max": 1.4870572090148926, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7614.51416015625, "min": 7614.51416015625, "max": 45111.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29909.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29909.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6024614572525024, "min": -0.06276325136423111, "max": 0.6925251483917236, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.11135864257812, "min": -15.251469612121582, "max": 197.369384765625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0022226448636502028, "min": -0.022937607020139694, "max": 0.20568019151687622, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.6423443555831909, "min": -6.10140323638916, "max": 49.77460479736328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0703352025351099, "min": 0.06316042142792695, "max": 0.07145457921754285, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9846928354915386, "min": 0.49642742036734094, "max": 1.0671526992615934, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014513855894273588, "min": 0.002702796227669502, "max": 0.016261397410568607, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20319398251983023, "min": 0.030207650087107338, "max": 0.24048236912737292, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.510811782142856e-06, "min": 7.510811782142856e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010515136494999999, "min": 0.00010515136494999999, "max": 0.0036356872881043003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250357142857143, "min": 0.10250357142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.43505, "min": 1.3886848, "max": 2.6173558, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002601067857142858, "min": 0.0002601067857142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003641495000000001, "min": 0.003641495000000001, "max": 0.12120838043, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009214939549565315, "min": 0.009214939549565315, "max": 0.26624172925949097, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1290091574192047, "min": 0.1290091574192047, "max": 1.8636921644210815, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.0388349514563, "min": 279.188679245283, "max": 990.3529411764706, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29977.0, "min": 16836.0, "max": 32343.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.631271825759735, "min": -0.8736471095505882, "max": 1.7188623711603497, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 168.0209980532527, "min": -28.373401656746864, "max": 187.35599845647812, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.631271825759735, "min": -0.8736471095505882, "max": 1.7188623711603497, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 168.0209980532527, "min": -28.373401656746864, "max": 187.35599845647812, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02816064026269178, "min": 0.02816064026269178, "max": 4.815620334271123, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.900545947057253, "min": 2.8741972114730743, "max": 81.86554568260908, "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": "1732948814", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/meipodai/miniconda3/envs/RL_hugging_face/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1", "numpy_version": "1.23.5", "end_time_seconds": "1732950229" }, "total": 1415.0880622710001, "count": 1, "self": 10.004420376000098, "children": { "run_training.setup": { "total": 0.032598813999999976, "count": 1, "self": 0.032598813999999976 }, "TrainerController.start_learning": { "total": 1405.051043081, "count": 1, "self": 1.2964867709927148, "children": { "TrainerController._reset_env": { "total": 2.8264024740000018, "count": 1, "self": 2.8264024740000018 }, "TrainerController.advance": { "total": 1400.8851057750076, "count": 64262, "self": 1.18059249301632, "children": { "env_step": { "total": 963.7096255620025, "count": 64262, "self": 881.5128409020095, "children": { "SubprocessEnvManager._take_step": { "total": 81.3500683299908, "count": 64262, "self": 3.166471224001029, "children": { "TorchPolicy.evaluate": { "total": 78.18359710598978, "count": 62550, "self": 78.18359710598978 } } }, "workers": { "total": 0.8467163300021809, "count": 64262, "self": 0.0, "children": { "worker_root": { "total": 1402.7001108620107, "count": 64262, "is_parallel": true, "self": 601.4081681390137, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001876853999995376, "count": 1, "is_parallel": true, "self": 0.0009676179999900114, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009092360000053645, "count": 8, "is_parallel": true, "self": 0.0009092360000053645 } } }, "UnityEnvironment.step": { "total": 0.026073773000000244, "count": 1, "is_parallel": true, "self": 0.0002419609999932959, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023253400000555757, "count": 1, "is_parallel": true, "self": 0.00023253400000555757 }, "communicator.exchange": { "total": 0.024746069000002535, "count": 1, "is_parallel": true, "self": 0.024746069000002535 }, "steps_from_proto": { "total": 0.0008532089999988557, "count": 1, "is_parallel": true, "self": 0.00021301600000356302, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006401929999952927, "count": 8, "is_parallel": true, "self": 0.0006401929999952927 } } } } } } }, "UnityEnvironment.step": { "total": 801.291942722997, "count": 64261, "is_parallel": true, "self": 14.748339660982879, "children": { "UnityEnvironment._generate_step_input": { "total": 11.567087183001242, "count": 64261, "is_parallel": true, "self": 11.567087183001242 }, "communicator.exchange": { "total": 730.5581522219948, "count": 64261, "is_parallel": true, "self": 730.5581522219948 }, "steps_from_proto": { "total": 44.418363657018084, "count": 64261, "is_parallel": true, "self": 11.164899822033966, "children": { "_process_rank_one_or_two_observation": { "total": 33.25346383498412, "count": 514088, "is_parallel": true, "self": 33.25346383498412 } } } } } } } } } } }, "trainer_advance": { "total": 435.9948877199887, "count": 64262, "self": 2.3408098649925932, "children": { "process_trajectory": { "total": 74.24076526499366, "count": 64262, "self": 74.09923748799358, "children": { "RLTrainer._checkpoint": { "total": 0.14152777700007846, "count": 2, "self": 0.14152777700007846 } } }, "_update_policy": { "total": 359.4133125900024, "count": 460, "self": 168.01278894600313, "children": { "TorchPPOOptimizer.update": { "total": 191.4005236439993, "count": 22785, "self": 191.4005236439993 } } } } } } }, "trainer_threads": { "total": 6.010000106471125e-07, "count": 1, "self": 6.010000106471125e-07 }, "TrainerController._save_models": { "total": 0.043047459999797866, "count": 1, "self": 0.0013044739996530552, "children": { "RLTrainer._checkpoint": { "total": 0.04174298600014481, "count": 1, "self": 0.04174298600014481 } } } } } } }