Reinforcement Learning
ml-agents
TensorBoard
ONNX
Pyramids
deep-reinforcement-learning
ML-Agents-Pyramids
Instructions to use sourav6565/ppo-Pyramids with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use sourav6565/ppo-Pyramids with ml-agents:
mlagents-load-from-hf --repo-id="sourav6565/ppo-Pyramids" --local-dir="./download: string[]s"
- Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 1.0074084997177124, | |
| "min": 1.0074084997177124, | |
| "max": 1.5045548677444458, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 32978.5234375, | |
| "min": 32142.97265625, | |
| "max": 48386.484375, | |
| "count": 3 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 89933.0, | |
| "min": 29952.0, | |
| "max": 89933.0, | |
| "count": 3 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 89933.0, | |
| "min": 29952.0, | |
| "max": 89933.0, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": -0.0701688677072525, | |
| "min": -0.0701688677072525, | |
| "max": 0.02310718409717083, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": -16.91069793701172, | |
| "min": -16.91069793701172, | |
| "max": 5.476402759552002, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.15606334805488586, | |
| "min": 0.15606334805488586, | |
| "max": 0.24710997939109802, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 37.61126708984375, | |
| "min": 37.61126708984375, | |
| "max": 59.553504943847656, | |
| "count": 3 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07103993055023976, | |
| "min": 0.06715091460365681, | |
| "max": 0.07103993055023976, | |
| "count": 3 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.852479166602877, | |
| "min": 0.6715091460365681, | |
| "max": 0.852479166602877, | |
| "count": 3 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.0014539880073098262, | |
| "min": 0.0013835741392416068, | |
| "max": 0.0033888894993735403, | |
| "count": 3 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.017447856087717914, | |
| "min": 0.013835741392416067, | |
| "max": 0.0338888949937354, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.431157522949998e-05, | |
| "min": 7.431157522949998e-05, | |
| "max": 0.00024958081680640003, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.0008917389027539998, | |
| "min": 0.0008917389027539998, | |
| "max": 0.002495808168064, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1247705, | |
| "min": 0.1247705, | |
| "max": 0.1831936, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.497246, | |
| "min": 1.497246, | |
| "max": 1.831936, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.00248457295, | |
| "min": 0.00248457295, | |
| "max": 0.00832104064, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.029814875400000003, | |
| "min": 0.029814875400000003, | |
| "max": 0.08321040639999999, | |
| "count": 3 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.11807534843683243, | |
| "min": 0.11807534843683243, | |
| "max": 0.3486832082271576, | |
| "count": 3 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 1.4169042110443115, | |
| "min": 1.4169042110443115, | |
| "max": 3.4868321418762207, | |
| "count": 3 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 984.5294117647059, | |
| "min": 970.9411764705883, | |
| "max": 999.0, | |
| "count": 3 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 33474.0, | |
| "min": 16506.0, | |
| "max": 33474.0, | |
| "count": 3 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": -0.8649875493720174, | |
| "min": -1.0000000521540642, | |
| "max": -0.8642727793617682, | |
| "count": 3 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": -27.679601579904556, | |
| "min": -28.52100171893835, | |
| "max": -16.000000834465027, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": -0.8649875493720174, | |
| "min": -1.0000000521540642, | |
| "max": -0.8642727793617682, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": -27.679601579904556, | |
| "min": -28.52100171893835, | |
| "max": -16.000000834465027, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 1.3802067132201046, | |
| "min": 1.3802067132201046, | |
| "max": 7.513105393387377, | |
| "count": 3 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 44.166614823043346, | |
| "min": 44.166614823043346, | |
| "max": 120.20968629419804, | |
| "count": 3 | |
| }, | |
| "Pyramids.IsTraining.mean": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 3 | |
| }, | |
| "Pyramids.IsTraining.sum": { | |
| "value": 1.0, | |
| "min": 1.0, | |
| "max": 1.0, | |
| "count": 3 | |
| } | |
| }, | |
| "metadata": { | |
| "timer_format_version": "0.1.0", | |
| "start_time_seconds": "1782743183", | |
| "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", | |
| "command_line_arguments": "/kaggle/working/mla-env/bin/mlagents-learn ./Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --force", | |
| "mlagents_version": "1.1.0", | |
| "mlagents_envs_version": "1.1.0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.0.1+cpu", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1782743413" | |
| }, | |
| "total": 229.50573281700008, | |
| "count": 1, | |
| "self": 0.4319323730001088, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.01979816499988374, | |
| "count": 1, | |
| "self": 0.01979816499988374 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 229.0540022790001, | |
| "count": 1, | |
| "self": 0.19514993198481534, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 0.8195344599998862, | |
| "count": 1, | |
| "self": 0.8195344599998862 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 227.93119255901547, | |
| "count": 6314, | |
| "self": 0.09381608601097469, | |
| "children": { | |
| "env_step": { | |
| "total": 227.8373764730045, | |
| "count": 6314, | |
| "self": 189.11024421599404, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 38.636046056000396, | |
| "count": 6314, | |
| "self": 0.5378266589918894, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 38.098219397008506, | |
| "count": 6307, | |
| "self": 38.098219397008506 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.09108620101005727, | |
| "count": 6314, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 228.67530012597172, | |
| "count": 6314, | |
| "is_parallel": true, | |
| "self": 61.61487843597615, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0028680969999186345, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0008209599986912508, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0020471370012273837, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0020471370012273837 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05541134399982184, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006286539996835927, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0004427409999152587, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0004427409999152587 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.051955608000298525, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.051955608000298525 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0023843409999244614, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006516989997180644, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.001732642000206397, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.001732642000206397 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 167.06042168999556, | |
| "count": 6313, | |
| "is_parallel": true, | |
| "self": 3.052217865008515, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 2.383013760009362, | |
| "count": 6313, | |
| "is_parallel": true, | |
| "self": 2.383013760009362 | |
| }, | |
| "communicator.exchange": { | |
| "total": 151.73517875799553, | |
| "count": 6313, | |
| "is_parallel": true, | |
| "self": 151.73517875799553 | |
| }, | |
| "steps_from_proto": { | |
| "total": 9.89001130698216, | |
| "count": 6313, | |
| "is_parallel": true, | |
| "self": 2.0591350150430117, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 7.830876291939148, | |
| "count": 50504, | |
| "is_parallel": true, | |
| "self": 7.830876291939148 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 8.806400001049042e-05, | |
| "count": 1, | |
| "self": 8.806400001049042e-05, | |
| "children": { | |
| "thread_root": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "trainer_advance": { | |
| "total": 227.61324459106254, | |
| "count": 58757, | |
| "is_parallel": true, | |
| "self": 1.214625955091833, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 63.256215988970325, | |
| "count": 58757, | |
| "is_parallel": true, | |
| "self": 63.256215988970325 | |
| }, | |
| "_update_policy": { | |
| "total": 163.14240264700038, | |
| "count": 35, | |
| "is_parallel": true, | |
| "self": 56.08502922399248, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 107.0573734230079, | |
| "count": 2274, | |
| "is_parallel": true, | |
| "self": 107.0573734230079 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.1080372639999041, | |
| "count": 1, | |
| "self": 0.0013814940002703224, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.10665576999963378, | |
| "count": 1, | |
| "self": 0.10665576999963378 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |