{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37492474913597107, "min": 0.36654171347618103, "max": 1.472686529159546, "count": 34 }, "Pyramids.Policy.Entropy.sum": { "value": 11295.732421875, "min": 10978.6572265625, "max": 44675.41796875, "count": 34 }, "Pyramids.Step.mean": { "value": 1019999.0, "min": 29952.0, "max": 1019999.0, "count": 34 }, "Pyramids.Step.sum": { "value": 1019999.0, "min": 29952.0, "max": 1019999.0, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03032447025179863, "min": -0.20310690999031067, "max": -0.03032447025179863, "count": 34 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -7.429495334625244, "min": -48.13633728027344, "max": -7.429495334625244, "count": 34 }, "Pyramids.Policy.CuriosityValueEstimate.mean": { "value": 0.1564064770936966, "min": 0.1564064770936966, "max": 0.44639909267425537, "count": 34 }, "Pyramids.Policy.CuriosityValueEstimate.sum": { "value": 38.31958770751953, "min": 38.210716247558594, "max": 108.02857971191406, "count": 34 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06718603229835869, "min": 0.06478804335382495, "max": 0.07394896972318263, "count": 34 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9406044521770217, "min": 0.49618800863758766, "max": 1.0529568219661836, "count": 34 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.002840339800961007, "min": 0.00012460844201482606, "max": 0.004310364597613544, "count": 34 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0397647572134541, "min": 0.0017445181882075648, "max": 0.06034510436658962, "count": 34 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2261868068504335e-05, "min": 1.2261868068504335e-05, "max": 0.0002953752805594308, "count": 34 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00017166615295906068, "min": 0.00017166615295906068, "max": 0.0036590319529362673, "count": 34 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10408725738525391, "min": 0.10408725738525391, "max": 0.19845842633928573, "count": 34 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4572216033935548, "min": 1.3892089843750002, "max": 2.6196772575378415, "count": 34 }, "Pyramids.Policy.Beta.mean": { "value": 0.00041831701278686524, "min": 0.00041831701278686524, "max": 0.009845996791294642, "count": 34 }, "Pyramids.Policy.Beta.sum": { "value": 0.005856438179016113, "min": 0.005856438179016113, "max": 0.12198575802803038, "count": 34 }, "Pyramids.Losses.CuriosityForwardLoss.mean": { "value": 0.07406188456076836, "min": 0.07187406965550976, "max": 0.41989175825378267, "count": 34 }, "Pyramids.Losses.CuriosityForwardLoss.sum": { "value": 1.036866383850757, "min": 0.9707603916233661, "max": 2.9392423077764787, "count": 34 }, "Pyramids.Losses.CuriosityInverseLoss.mean": { "value": 0.06697648263649547, "min": 0.06312481397228102, "max": 0.7277615498644353, "count": 34 }, "Pyramids.Losses.CuriosityInverseLoss.sum": { "value": 0.9376707569109366, "min": 0.8529724184858529, "max": 5.0943308490510475, "count": 34 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 899.060606060606, "min": 881.741935483871, "max": 999.0, "count": 34 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29669.0, "min": 15984.0, "max": 33110.0, "count": 34 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4147697470404885, "min": -1.0000000521540642, "max": -0.23707746089466156, "count": 34 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -13.68740165233612, "min": -31.99360166490078, "max": -7.3494012877345085, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4147697470404885, "min": -1.0000000521540642, "max": -0.23707746089466156, "count": 34 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -13.68740165233612, "min": -31.99360166490078, "max": -7.3494012877345085, "count": 34 }, "Pyramids.Policy.CuriosityReward.mean": { "value": 1.3701743991537527, "min": 1.3701743991537527, "max": 6.27729257196188, "count": 34 }, "Pyramids.Policy.CuriosityReward.sum": { "value": 45.21575517207384, "min": 45.21575517207384, "max": 174.45192439109087, "count": 34 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 34 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1738524599", "python_version": "3.10.16 (main, Dec 4 2024, 08:53:38) [GCC 13.2.0]", "command_line_arguments": "/home/hrichter/projects/hf_rl_course/.venv/bin/mlagents-learn ml-agents/config/ppo/Pyramids.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+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738525559" }, "total": 960.69417054, "count": 1, "self": 0.21820811000020512, "children": { "run_training.setup": { "total": 0.014896433999865621, "count": 1, "self": 0.014896433999865621 }, "TrainerController.start_learning": { "total": 960.4610659959999, "count": 1, "self": 0.6438697869684802, "children": { "TrainerController._reset_env": { "total": 1.2939183309999862, "count": 1, "self": 1.2939183309999862 }, "TrainerController.advance": { "total": 958.4810456990313, "count": 66200, "self": 0.6672122379852681, "children": { "env_step": { "total": 516.2186331370485, "count": 66200, "self": 472.8256553351712, "children": { "SubprocessEnvManager._take_step": { "total": 42.98896845993613, "count": 66200, "self": 2.0265824469049676, "children": { "TorchPolicy.evaluate": { "total": 40.962386013031164, "count": 65598, "self": 40.962386013031164 } } }, "workers": { "total": 0.40400934194121874, "count": 66200, "self": 0.0, "children": { "worker_root": { "total": 959.4559383770147, "count": 66200, "is_parallel": true, "self": 533.8106512569464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009145409999291587, "count": 1, "is_parallel": true, "self": 0.00022774500007471943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006867959998544393, "count": 8, "is_parallel": true, "self": 0.0006867959998544393 } } }, "UnityEnvironment.step": { "total": 0.018782304000069416, "count": 1, "is_parallel": true, "self": 0.0003025040000466106, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002825439999014634, "count": 1, "is_parallel": true, "self": 0.0002825439999014634 }, "communicator.exchange": { "total": 0.01733245400009764, "count": 1, "is_parallel": true, "self": 0.01733245400009764 }, "steps_from_proto": { "total": 0.0008648020000237011, "count": 1, "is_parallel": true, "self": 0.0001828549998208473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006819470002028538, "count": 8, "is_parallel": true, "self": 0.0006819470002028538 } } } } } } }, "UnityEnvironment.step": { "total": 425.64528712006836, "count": 66199, "is_parallel": true, "self": 11.960250902025791, "children": { "UnityEnvironment._generate_step_input": { "total": 8.491987588990696, "count": 66199, "is_parallel": true, "self": 8.491987588990696 }, "communicator.exchange": { "total": 370.419048640038, "count": 66199, "is_parallel": true, "self": 370.419048640038 }, "steps_from_proto": { "total": 34.77399998901387, "count": 66199, "is_parallel": true, "self": 7.488494236913766, "children": { "_process_rank_one_or_two_observation": { "total": 27.285505752100107, "count": 529592, "is_parallel": true, "self": 27.285505752100107 } } } } } } } } } } }, "trainer_advance": { "total": 441.59520032399746, "count": 66200, "self": 1.3063789900720622, "children": { "process_trajectory": { "total": 63.53832344492298, "count": 66200, "self": 63.442949675923046, "children": { "RLTrainer._checkpoint": { "total": 0.09537376899993433, "count": 2, "self": 0.09537376899993433 } } }, "_update_policy": { "total": 376.7504978890024, "count": 469, "self": 251.99174821898123, "children": { "TorchPPOOptimizer.update": { "total": 124.75874967002119, "count": 23895, "self": 124.75874967002119 } } } } } } }, "trainer_threads": { "total": 7.300000106624793e-07, "count": 1, "self": 7.300000106624793e-07 }, "TrainerController._save_models": { "total": 0.04223144900015541, "count": 1, "self": 0.0018124279999938153, "children": { "RLTrainer._checkpoint": { "total": 0.04041902100016159, "count": 1, "self": 0.04041902100016159 } } } } } } }