{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3966046571731567, "min": 1.3966046571731567, "max": 1.4247130155563354, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70997.796875, "min": 68068.40625, "max": 75829.546875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.68925619834711, "min": 81.68925619834711, "max": 407.4146341463415, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49422.0, "min": 48929.0, "max": 50112.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999927.0, "min": 49485.0, "max": 1999927.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999927.0, "min": 49485.0, "max": 1999927.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.459555149078369, "min": 0.05064838379621506, "max": 2.4705350399017334, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1488.0308837890625, "min": 6.179102897644043, "max": 1488.0308837890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.801081833268, "min": 1.8450358539331155, "max": 3.904316358462624, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2299.65450912714, "min": 225.0943741798401, "max": 2299.65450912714, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.801081833268, "min": 1.8450358539331155, "max": 3.904316358462624, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2299.65450912714, "min": 225.0943741798401, "max": 2299.65450912714, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01332352499642487, "min": 0.012322203620472767, "max": 0.019506979877284416, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.02664704999284974, "min": 0.024644407240945534, "max": 0.058520939631853244, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05616571884602308, "min": 0.022208547219634056, "max": 0.06125190344949563, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.11233143769204616, "min": 0.04441709443926811, "max": 0.1755008205771446, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.6604484465500014e-06, "min": 4.6604484465500014e-06, "max": 0.00029528587657137495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.320896893100003e-06, "min": 9.320896893100003e-06, "max": 0.0008439966186678, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10155344999999999, "min": 0.10155344999999999, "max": 0.19842862500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20310689999999998, "min": 0.20310689999999998, "max": 0.5813322000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.751715500000005e-05, "min": 8.751715500000005e-05, "max": 0.004921588387499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001750343100000001, "min": 0.0001750343100000001, "max": 0.014068476780000002, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686556065", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1686558628" }, "total": 2562.3202097050003, "count": 1, "self": 0.8315725820002626, "children": { "run_training.setup": { "total": 0.04167541800001118, "count": 1, "self": 0.04167541800001118 }, "TrainerController.start_learning": { "total": 2561.446961705, "count": 1, "self": 4.610859899063598, "children": { "TrainerController._reset_env": { "total": 3.9767442640000468, "count": 1, "self": 3.9767442640000468 }, "TrainerController.advance": { "total": 2552.6772733569364, "count": 232424, "self": 4.849381925940634, "children": { "env_step": { "total": 2013.448827064967, "count": 232424, "self": 1697.6015381389693, "children": { "SubprocessEnvManager._take_step": { "total": 312.82974308597977, "count": 232424, "self": 17.611660251052115, "children": { "TorchPolicy.evaluate": { "total": 295.21808283492766, "count": 223006, "self": 295.21808283492766 } } }, "workers": { "total": 3.017545840017874, "count": 232424, "self": 0.0, "children": { "worker_root": { "total": 2552.946578483989, "count": 232424, "is_parallel": true, "self": 1164.573148286948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009611739999968449, "count": 1, "is_parallel": true, "self": 0.00027946899996322827, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006817050000336167, "count": 2, "is_parallel": true, "self": 0.0006817050000336167 } } }, "UnityEnvironment.step": { "total": 0.030733042999997906, "count": 1, "is_parallel": true, "self": 0.00032634100000450417, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024081300000489136, "count": 1, "is_parallel": true, "self": 0.00024081300000489136 }, "communicator.exchange": { "total": 0.029370739999990292, "count": 1, "is_parallel": true, "self": 0.029370739999990292 }, "steps_from_proto": { "total": 0.0007951489999982186, "count": 1, "is_parallel": true, "self": 0.00027798300004633347, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005171659999518852, "count": 2, "is_parallel": true, "self": 0.0005171659999518852 } } } } } } }, "UnityEnvironment.step": { "total": 1388.373430197041, "count": 232423, "is_parallel": true, "self": 40.841559905094755, "children": { "UnityEnvironment._generate_step_input": { "total": 86.2333091629556, "count": 232423, "is_parallel": true, "self": 86.2333091629556 }, "communicator.exchange": { "total": 1159.5519844809835, "count": 232423, "is_parallel": true, "self": 1159.5519844809835 }, "steps_from_proto": { "total": 101.74657664800719, "count": 232423, "is_parallel": true, "self": 39.01664263095199, "children": { "_process_rank_one_or_two_observation": { "total": 62.7299340170552, "count": 464846, "is_parallel": true, "self": 62.7299340170552 } } } } } } } } } } }, "trainer_advance": { "total": 534.3790643660291, "count": 232424, "self": 7.390682569023284, "children": { "process_trajectory": { "total": 146.43087864300668, "count": 232424, "self": 144.96691370100626, "children": { "RLTrainer._checkpoint": { "total": 1.4639649420004162, "count": 10, "self": 1.4639649420004162 } } }, "_update_policy": { "total": 380.55750315399916, "count": 96, "self": 321.2139232069926, "children": { "TorchPPOOptimizer.update": { "total": 59.34357994700656, "count": 2880, "self": 59.34357994700656 } } } } } } }, "trainer_threads": { "total": 1.7239999579032883e-06, "count": 1, "self": 1.7239999579032883e-06 }, "TrainerController._save_models": { "total": 0.1820824609999363, "count": 1, "self": 0.0028144009997959074, "children": { "RLTrainer._checkpoint": { "total": 0.1792680600001404, "count": 1, "self": 0.1792680600001404 } } } } } } }