{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.4204990863800049, "min": 0.41473114490509033, "max": 0.5147774815559387, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4061.18017578125, "min": 4042.697265625, "max": 5294.486328125, "count": 50 }, "SnowballTarget.Step.mean": { "value": 999992.0, "min": 509968.0, "max": 999992.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 999992.0, "min": 509968.0, "max": 999992.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.856378555297852, "min": 13.292767524719238, "max": 13.918790817260742, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2840.5576171875, "min": 2578.796875, "max": 2853.35205078125, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0718381038335079, "min": 0.05937582174697038, "max": 0.07631100223380581, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3591905191675395, "min": 0.2375032869878815, "max": 0.38155501116902907, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1773360082916185, "min": 0.1512796406652413, "max": 0.19390156032407985, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8866800414580925, "min": 0.6522421940576797, "max": 0.9695078016203992, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.521699492799996e-06, "min": 1.521699492799996e-06, "max": 0.0001483716505428, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.60849746399998e-06, "min": 7.60849746399998e-06, "max": 0.0007270082576640001, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10050719999999999, "min": 0.10050719999999999, "max": 0.1494572, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.502536, "min": 0.40598880000000004, "max": 0.7423360000000001, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.530927999999995e-05, "min": 3.530927999999995e-05, "max": 0.0024779142800000005, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00017654639999999973, "min": 0.00017654639999999973, "max": 0.0121425664, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.054545454545455, "min": 25.65909090909091, "max": 27.5, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1488.0, "min": 1129.0, "max": 1503.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.054545454545455, "min": 25.65909090909091, "max": 27.5, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1488.0, "min": 1129.0, "max": 1503.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690891385", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "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": "1690892546" }, "total": 1160.662677215, "count": 1, "self": 0.4239330450000125, "children": { "run_training.setup": { "total": 0.03380916800006162, "count": 1, "self": 0.03380916800006162 }, "TrainerController.start_learning": { "total": 1160.204935002, "count": 1, "self": 1.3026766430307362, "children": { "TrainerController._reset_env": { "total": 3.896834601000137, "count": 1, "self": 3.896834601000137 }, "TrainerController.advance": { "total": 1154.8614462209687, "count": 45476, "self": 0.6355414419135741, "children": { "env_step": { "total": 1154.225904779055, "count": 45476, "self": 836.7392049760897, "children": { "SubprocessEnvManager._take_step": { "total": 316.8335550379654, "count": 45476, "self": 4.2225153679412415, "children": { "TorchPolicy.evaluate": { "total": 312.6110396700242, "count": 45476, "self": 312.6110396700242 } } }, "workers": { "total": 0.6531447649999791, "count": 45476, "self": 0.0, "children": { "worker_root": { "total": 1156.4292470499945, "count": 45476, "is_parallel": true, "self": 549.7946691019188, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001821205000169357, "count": 1, "is_parallel": true, "self": 0.0005339730000741838, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012872320000951731, "count": 10, "is_parallel": true, "self": 0.0012872320000951731 } } }, "UnityEnvironment.step": { "total": 0.03880305200004841, "count": 1, "is_parallel": true, "self": 0.0006078620001517265, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004058579997945344, "count": 1, "is_parallel": true, "self": 0.0004058579997945344 }, "communicator.exchange": { "total": 0.03573670800005857, "count": 1, "is_parallel": true, "self": 0.03573670800005857 }, "steps_from_proto": { "total": 0.002052624000043579, "count": 1, "is_parallel": true, "self": 0.0004982790001122339, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015543449999313452, "count": 10, "is_parallel": true, "self": 0.0015543449999313452 } } } } } } }, "UnityEnvironment.step": { "total": 606.6345779480757, "count": 45475, "is_parallel": true, "self": 25.990496037154344, "children": { "UnityEnvironment._generate_step_input": { "total": 12.880096801027548, "count": 45475, "is_parallel": true, "self": 12.880096801027548 }, "communicator.exchange": { "total": 481.7465131599515, "count": 45475, "is_parallel": true, "self": 481.7465131599515 }, "steps_from_proto": { "total": 86.01747194994232, "count": 45475, "is_parallel": true, "self": 15.769068050099577, "children": { "_process_rank_one_or_two_observation": { "total": 70.24840389984274, "count": 454750, "is_parallel": true, "self": 70.24840389984274 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013637900019602966, "count": 1, "self": 0.00013637900019602966, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1145.7589073039617, "count": 1062056, "is_parallel": true, "self": 23.823828691894278, "children": { "process_trajectory": { "total": 615.1835517040679, "count": 1062056, "is_parallel": true, "self": 611.9219108580676, "children": { "RLTrainer._checkpoint": { "total": 3.2616408460003186, "count": 10, "is_parallel": true, "self": 3.2616408460003186 } } }, "_update_policy": { "total": 506.7515269079995, "count": 227, "is_parallel": true, "self": 204.23789698899714, "children": { "TorchPPOOptimizer.update": { "total": 302.51362991900237, "count": 11571, "is_parallel": true, "self": 302.51362991900237 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1438411580002139, "count": 1, "self": 0.001152744000137318, "children": { "RLTrainer._checkpoint": { "total": 0.1426884140000766, "count": 1, "self": 0.1426884140000766 } } } } } } }