{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5847466588020325, "min": 0.5484316945075989, "max": 1.4259932041168213, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17701.451171875, "min": 16549.474609375, "max": 43258.9296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989980.0, "min": 29952.0, "max": 989980.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.10137712210416794, "min": -0.09946084022521973, "max": 0.16388164460659027, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 25.547035217285156, "min": -24.069522857666016, "max": 41.13429260253906, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005126485135406256, "min": 0.005126485135406256, "max": 0.3878185451030731, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2918742895126343, "min": 1.2918742895126343, "max": 93.46427154541016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06788425448688767, "min": 0.065506779966962, "max": 0.0731779508267251, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9503795628164274, "min": 0.5122456557870757, "max": 1.0544116736176268, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010262815306629947, "min": 8.228682940963877e-05, "max": 0.010262815306629947, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14367941429281925, "min": 0.001069728782325304, "max": 0.14367941429281925, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.678340297728573e-06, "min": 7.678340297728573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001074967641682, "min": 0.0001074967641682, "max": 0.0036331723889426, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255941428571427, "min": 0.10255941428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4358317999999999, "min": 1.3886848, "max": 2.6110574, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026568548714285713, "min": 0.00026568548714285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00371959682, "min": 0.00371959682, "max": 0.12112463426, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01572125405073166, "min": 0.01572125405073166, "max": 0.48555904626846313, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22009755671024323, "min": 0.22009755671024323, "max": 3.3989133834838867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 692.9555555555555, "min": 662.3111111111111, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31183.0, "min": 15984.0, "max": 32987.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5175869179808575, "min": -1.0000000521540642, "max": 0.6707599649826685, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 23.808998227119446, "min": -29.63560152053833, "max": 30.184198424220085, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5175869179808575, "min": -1.0000000521540642, "max": 0.6707599649826685, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 23.808998227119446, "min": -29.63560152053833, "max": 30.184198424220085, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11421679924229544, "min": 0.11361928350266276, "max": 10.360735669732094, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.2539727651455905, "min": 4.8159597653429955, "max": 165.7717707157135, "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": "1700666893", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700669056" }, "total": 2163.3517619149998, "count": 1, "self": 0.6626173309996375, "children": { "run_training.setup": { "total": 0.045521131999976205, "count": 1, "self": 0.045521131999976205 }, "TrainerController.start_learning": { "total": 2162.643623452, "count": 1, "self": 1.3897045729922866, "children": { "TrainerController._reset_env": { "total": 4.535021712000116, "count": 1, "self": 4.535021712000116 }, "TrainerController.advance": { "total": 2156.613530124008, "count": 63324, "self": 1.4594561450389847, "children": { "env_step": { "total": 1503.1037801840314, "count": 63324, "self": 1365.9781641359777, "children": { "SubprocessEnvManager._take_step": { "total": 136.25996843400958, "count": 63324, "self": 4.690448323959799, "children": { "TorchPolicy.evaluate": { "total": 131.56952011004978, "count": 62570, "self": 131.56952011004978 } } }, "workers": { "total": 0.8656476140440645, "count": 63324, "self": 0.0, "children": { "worker_root": { "total": 2157.595939656106, "count": 63324, "is_parallel": true, "self": 915.4594514521364, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020100910001019656, "count": 1, "is_parallel": true, "self": 0.0006657010003436881, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013443899997582776, "count": 8, "is_parallel": true, "self": 0.0013443899997582776 } } }, "UnityEnvironment.step": { "total": 0.09648532999995041, "count": 1, "is_parallel": true, "self": 0.0006466289999025321, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005136669999501464, "count": 1, "is_parallel": true, "self": 0.0005136669999501464 }, "communicator.exchange": { "total": 0.09329858199998853, "count": 1, "is_parallel": true, "self": 0.09329858199998853 }, "steps_from_proto": { "total": 0.0020264520001092023, "count": 1, "is_parallel": true, "self": 0.0004661049999867828, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015603470001224196, "count": 8, "is_parallel": true, "self": 0.0015603470001224196 } } } } } } }, "UnityEnvironment.step": { "total": 1242.1364882039697, "count": 63323, "is_parallel": true, "self": 35.06031763084252, "children": { "UnityEnvironment._generate_step_input": { "total": 25.488893052048752, "count": 63323, "is_parallel": true, "self": 25.488893052048752 }, "communicator.exchange": { "total": 1078.7499483800332, "count": 63323, "is_parallel": true, "self": 1078.7499483800332 }, "steps_from_proto": { "total": 102.8373291410453, "count": 63323, "is_parallel": true, "self": 20.853697076068556, "children": { "_process_rank_one_or_two_observation": { "total": 81.98363206497675, "count": 506584, "is_parallel": true, "self": 81.98363206497675 } } } } } } } } } } }, "trainer_advance": { "total": 652.0502937949375, "count": 63324, "self": 2.8140030299234695, "children": { "process_trajectory": { "total": 130.9289478980154, "count": 63324, "self": 130.72906162401523, "children": { "RLTrainer._checkpoint": { "total": 0.19988627400016412, "count": 2, "self": 0.19988627400016412 } } }, "_update_policy": { "total": 518.3073428669986, "count": 452, "self": 310.32285965996243, "children": { "TorchPPOOptimizer.update": { "total": 207.9844832070362, "count": 22764, "self": 207.9844832070362 } } } } } } }, "trainer_threads": { "total": 1.1550000635907054e-06, "count": 1, "self": 1.1550000635907054e-06 }, "TrainerController._save_models": { "total": 0.1053658880000512, "count": 1, "self": 0.001832858999932796, "children": { "RLTrainer._checkpoint": { "total": 0.1035330290001184, "count": 1, "self": 0.1035330290001184 } } } } } } }