{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3839273750782013, "min": 0.37404122948646545, "max": 1.4288702011108398, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11401.107421875, "min": 11334.9453125, "max": 43346.20703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989930.0, "min": 29952.0, "max": 989930.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.614491879940033, "min": -0.19480715692043304, "max": 0.6550472378730774, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.4432373046875, "min": -46.16929626464844, "max": 187.99855041503906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.07318393141031265, "min": -0.07318393141031265, "max": 0.48806479573249817, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -20.418315887451172, "min": -20.418315887451172, "max": 115.67135620117188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07170302507819586, "min": 0.06538753967105197, "max": 0.07364958621869604, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.003842351094742, "min": 0.5067810199560328, "max": 1.0698948174991243, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017201309361899758, "min": 0.0002177438254461774, "max": 0.01736067041374987, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2408183310665966, "min": 0.002830669730800306, "max": 0.24304938579249818, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5467260558857155e-06, "min": 7.5467260558857155e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010565416478240002, "min": 0.00010565416478240002, "max": 0.0034887847370717994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251554285714286, "min": 0.10251554285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352176, "min": 1.3886848, "max": 2.5722967999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026130273142857145, "min": 0.00026130273142857145, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036582382400000006, "min": 0.0036582382400000006, "max": 0.11630652718000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01037752814590931, "min": 0.01037752814590931, "max": 0.488626629114151, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14528539776802063, "min": 0.14528539776802063, "max": 3.42038631439209, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 303.81052631578945, "min": 288.7864077669903, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28862.0, "min": 15984.0, "max": 32479.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6472708196379244, "min": -1.0000000521540642, "max": 1.6917863927275232, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.13799868524075, "min": -31.99680168926716, "max": 174.2539984509349, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6472708196379244, "min": -1.0000000521540642, "max": 1.6917863927275232, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.13799868524075, "min": -31.99680168926716, "max": 174.2539984509349, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03318959897599901, "min": 0.03318959897599901, "max": 10.078412741422653, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.186201501695905, "min": 3.186201501695905, "max": 161.25460386276245, "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": "1685010429", "python_version": "3.10.11 (main, Apr 20 2023, 19:02:41) [GCC 11.2.0]", "command_line_arguments": "/home/stephen/miniconda3/envs/deep-rl-course/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --width=1280 --height=720 --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1685011640" }, "total": 1210.4989048200077, "count": 1, "self": 0.3192543479963206, "children": { "run_training.setup": { "total": 0.013383196012000553, "count": 1, "self": 0.013383196012000553 }, "TrainerController.start_learning": { "total": 1210.1662672759994, "count": 1, "self": 1.281517392519163, "children": { "TrainerController._reset_env": { "total": 6.316212777004694, "count": 1, "self": 6.316212777004694 }, "TrainerController.advance": { "total": 1202.5078337914747, "count": 64031, "self": 1.3369778820488136, "children": { "env_step": { "total": 754.3337355441035, "count": 64031, "self": 634.0964460049872, "children": { "SubprocessEnvManager._take_step": { "total": 119.41647095949156, "count": 64031, "self": 3.2679904958058614, "children": { "TorchPolicy.evaluate": { "total": 116.1484804636857, "count": 62552, "self": 116.1484804636857 } } }, "workers": { "total": 0.8208185796247562, "count": 64031, "self": 0.0, "children": { "worker_root": { "total": 1208.4328184529732, "count": 64031, "is_parallel": true, "self": 650.8204816541256, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010614399943733588, "count": 1, "is_parallel": true, "self": 0.00029204398742876947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007693960069445893, "count": 8, "is_parallel": true, "self": 0.0007693960069445893 } } }, "UnityEnvironment.step": { "total": 0.02114481398893986, "count": 1, "is_parallel": true, "self": 0.0002786679979180917, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026757999148685485, "count": 1, "is_parallel": true, "self": 0.00026757999148685485 }, "communicator.exchange": { "total": 0.019706410996150225, "count": 1, "is_parallel": true, "self": 0.019706410996150225 }, "steps_from_proto": { "total": 0.000892155003384687, "count": 1, "is_parallel": true, "self": 0.00018864199228119105, "children": { "_process_rank_one_or_two_observation": { "total": 0.000703513011103496, "count": 8, "is_parallel": true, "self": 0.000703513011103496 } } } } } } }, "UnityEnvironment.step": { "total": 557.6123367988475, "count": 64030, "is_parallel": true, "self": 17.024892047746107, "children": { "UnityEnvironment._generate_step_input": { "total": 12.262091512457118, "count": 64030, "is_parallel": true, "self": 12.262091512457118 }, "communicator.exchange": { "total": 476.64518081813003, "count": 64030, "is_parallel": true, "self": 476.64518081813003 }, "steps_from_proto": { "total": 51.68017242051428, "count": 64030, "is_parallel": true, "self": 11.26647077446978, "children": { "_process_rank_one_or_two_observation": { "total": 40.4137016460445, "count": 512240, "is_parallel": true, "self": 40.4137016460445 } } } } } } } } } } }, "trainer_advance": { "total": 446.83712036532233, "count": 64031, "self": 2.399169267504476, "children": { "process_trajectory": { "total": 84.02544081573433, "count": 64031, "self": 83.89241295873944, "children": { "RLTrainer._checkpoint": { "total": 0.13302785699488595, "count": 2, "self": 0.13302785699488595 } } }, "_update_policy": { "total": 360.41251028208353, "count": 450, "self": 212.57134403382952, "children": { "TorchPPOOptimizer.update": { "total": 147.841166248254, "count": 22797, "self": 147.841166248254 } } } } } } }, "trainer_threads": { "total": 6.90997694619e-07, "count": 1, "self": 6.90997694619e-07 }, "TrainerController._save_models": { "total": 0.06070262400317006, "count": 1, "self": 0.0008341020002262667, "children": { "RLTrainer._checkpoint": { "total": 0.05986852200294379, "count": 1, "self": 0.05986852200294379 } } } } } } }