{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5963050723075867, "min": 0.5963050723075867, "max": 1.3754076957702637, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18051.34765625, "min": 18051.34765625, "max": 41724.3671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989917.0, "min": 29958.0, "max": 989917.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989917.0, "min": 29958.0, "max": 989917.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.15474189817905426, "min": -0.12274166941642761, "max": 0.1562112718820572, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 38.84021759033203, "min": -29.70348358154297, "max": 39.52145004272461, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02592696249485016, "min": 0.013563553802669048, "max": 0.39649698138237, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.507667541503906, "min": 3.29594349861145, "max": 95.55577087402344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07065907691319079, "min": 0.06469281561977096, "max": 0.07250126322976924, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.989227076784671, "min": 0.5649014154526716, "max": 1.0782292399380822, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007352304163971432, "min": 0.00017133642381644452, "max": 0.014948464288884668, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10293225829560006, "min": 0.0022273735096137786, "max": 0.12771074511685723, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.223711877842857e-06, "min": 7.223711877842857e-06, "max": 0.000294767326744225, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001011319662898, "min": 0.0001011319662898, "max": 0.0036333271888910005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240787142857143, "min": 0.10240787142857143, "max": 0.198255775, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4337102, "min": 1.4337102, "max": 2.611109000000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025054635571428575, "min": 0.00025054635571428575, "max": 0.0098257519225, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035076489800000004, "min": 0.0035076489800000004, "max": 0.12112978910000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015463285148143768, "min": 0.015463285148143768, "max": 0.7606267929077148, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21648599207401276, "min": 0.21648599207401276, "max": 6.085014343261719, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 721.2857142857143, "min": 670.0869565217391, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30294.0, "min": 17524.0, "max": 32518.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.5165952020103023, "min": -0.9998125517740846, "max": 0.8080260517156642, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 21.696998484432697, "min": -31.994001656770706, "max": 37.169198378920555, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.5165952020103023, "min": -0.9998125517740846, "max": 0.8080260517156642, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 21.696998484432697, "min": -31.994001656770706, "max": 37.169198378920555, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.11527981605225553, "min": 0.10991443896858508, "max": 13.63461841477288, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.841752274194732, "min": 4.841752274194732, "max": 245.42313146591187, "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": "1695385765", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695388233" }, "total": 2468.0305308380002, "count": 1, "self": 0.6382784100005665, "children": { "run_training.setup": { "total": 0.04919151400008559, "count": 1, "self": 0.04919151400008559 }, "TrainerController.start_learning": { "total": 2467.3430609139996, "count": 1, "self": 1.895487738999691, "children": { "TrainerController._reset_env": { "total": 6.1620203089998995, "count": 1, "self": 6.1620203089998995 }, "TrainerController.advance": { "total": 2459.177967040999, "count": 63306, "self": 1.9662342410506426, "children": { "env_step": { "total": 1720.5459140899477, "count": 63306, "self": 1574.892380872975, "children": { "SubprocessEnvManager._take_step": { "total": 144.4542991000419, "count": 63306, "self": 5.966188868044128, "children": { "TorchPolicy.evaluate": { "total": 138.48811023199778, "count": 62563, "self": 138.48811023199778 } } }, "workers": { "total": 1.199234116930711, "count": 63306, "self": 0.0, "children": { "worker_root": { "total": 2461.034096194923, "count": 63306, "is_parallel": true, "self": 1031.7385939659346, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005112751000069693, "count": 1, "is_parallel": true, "self": 0.0036123939996741683, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015003570003955247, "count": 8, "is_parallel": true, "self": 0.0015003570003955247 } } }, "UnityEnvironment.step": { "total": 0.10747536500002752, "count": 1, "is_parallel": true, "self": 0.01179746600018916, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005697179999515356, "count": 1, "is_parallel": true, "self": 0.0005697179999515356 }, "communicator.exchange": { "total": 0.09192272399991452, "count": 1, "is_parallel": true, "self": 0.09192272399991452 }, "steps_from_proto": { "total": 0.0031854569999723026, "count": 1, "is_parallel": true, "self": 0.0004684160001033888, "children": { "_process_rank_one_or_two_observation": { "total": 0.002717040999868914, "count": 8, "is_parallel": true, "self": 0.002717040999868914 } } } } } } }, "UnityEnvironment.step": { "total": 1429.2955022289887, "count": 63305, "is_parallel": true, "self": 41.35684183197827, "children": { "UnityEnvironment._generate_step_input": { "total": 26.989455070002577, "count": 63305, "is_parallel": true, "self": 26.989455070002577 }, "communicator.exchange": { "total": 1237.4164844410295, "count": 63305, "is_parallel": true, "self": 1237.4164844410295 }, "steps_from_proto": { "total": 123.53272088597828, "count": 63305, "is_parallel": true, "self": 25.05759972295482, "children": { "_process_rank_one_or_two_observation": { "total": 98.47512116302346, "count": 506440, "is_parallel": true, "self": 98.47512116302346 } } } } } } } } } } }, "trainer_advance": { "total": 736.6658187100011, "count": 63306, "self": 3.5870474160190042, "children": { "process_trajectory": { "total": 124.86615392397971, "count": 63306, "self": 124.63452657597963, "children": { "RLTrainer._checkpoint": { "total": 0.23162734800007456, "count": 2, "self": 0.23162734800007456 } } }, "_update_policy": { "total": 608.2126173700024, "count": 455, "self": 393.9834452249604, "children": { "TorchPPOOptimizer.update": { "total": 214.22917214504196, "count": 22788, "self": 214.22917214504196 } } } } } } }, "trainer_threads": { "total": 9.58000327955233e-07, "count": 1, "self": 9.58000327955233e-07 }, "TrainerController._save_models": { "total": 0.1075848670002415, "count": 1, "self": 0.001607010000043374, "children": { "RLTrainer._checkpoint": { "total": 0.10597785700019813, "count": 1, "self": 0.10597785700019813 } } } } } } }