Seventh Push
Browse files- SoccerTwos.onnx +1 -1
- SoccerTwos/SoccerTwos-32499941.onnx +3 -0
- SoccerTwos/SoccerTwos-32499941.pt +3 -0
- SoccerTwos/checkpoint.pt +1 -1
- SoccerTwos/events.out.tfevents.1725639265.Bretts-MacBook-Pro.local.55651.0 +2 -2
- SoccerTwos/events.out.tfevents.1725741373.Bretts-MacBook-Pro.local.57198.0 +3 -0
- config.json +1 -1
- configuration.yaml +1 -1
- run_logs/Player-0.log +2 -2
- run_logs/timers.json +382 -61
- run_logs/training_status.json +8 -8
SoccerTwos.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2351062
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad5e42ffb14033363e95c48e20ea11212cf53e6b917d8f5d64f9916e59b9f24a
|
| 3 |
size 2351062
|
SoccerTwos/SoccerTwos-32499941.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f95c440705145507bffabafa0a86080d9a1227e68029c5f3bfac64618a1e8dd9
|
| 3 |
+
size 2351062
|
SoccerTwos/SoccerTwos-32499941.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:142f7de35a6a8c907c49c79d725f4a524117540d8f0de4caff367a5374f7a4da
|
| 3 |
+
size 36303154
|
SoccerTwos/checkpoint.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 36301318
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb99e03d8d1496bfffcf9fa933bef55f12e098b38c01731441fab8126e9b2ebd
|
| 3 |
size 36301318
|
SoccerTwos/events.out.tfevents.1725639265.Bretts-MacBook-Pro.local.55651.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deb15b8fc9deffc7b288f005a81b904742b64f7de964afc36987ac9f5138eff2
|
| 3 |
+
size 2417737
|
SoccerTwos/events.out.tfevents.1725741373.Bretts-MacBook-Pro.local.57198.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dffce8bdecae174dc92a44c9618b9282f32401478c297757966b567386f0265
|
| 3 |
+
size 1732159
|
config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "curiosity": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.
|
|
|
|
| 1 |
+
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 40960, "buffer_size": 163840, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "curiosity": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 1e-06, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.9, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "sept-run-01", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
CHANGED
|
@@ -74,7 +74,7 @@ behaviors:
|
|
| 74 |
team_change: 400000
|
| 75 |
swap_steps: 2000
|
| 76 |
window: 30
|
| 77 |
-
play_against_latest_model_ratio: 0.
|
| 78 |
initial_elo: 1.0
|
| 79 |
behavioral_cloning: null
|
| 80 |
env_settings:
|
|
|
|
| 74 |
team_change: 400000
|
| 75 |
swap_steps: 2000
|
| 76 |
window: 30
|
| 77 |
+
play_against_latest_model_ratio: 0.9
|
| 78 |
initial_elo: 1.0
|
| 79 |
behavioral_cloning: null
|
| 80 |
env_settings:
|
run_logs/Player-0.log
CHANGED
|
@@ -10,7 +10,7 @@ NullGfxDevice:
|
|
| 10 |
Renderer: Null Device
|
| 11 |
Vendor: Unity Technologies
|
| 12 |
Begin MonoManager ReloadAssembly
|
| 13 |
-
- Completed reload, in 0.
|
| 14 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
| 15 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
| 16 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
|
@@ -35,6 +35,6 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
|
|
| 35 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
| 36 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
| 37 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
| 38 |
-
UnloadTime: 0.
|
| 39 |
Registered Communicator in Agent.
|
| 40 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
|
|
|
| 10 |
Renderer: Null Device
|
| 11 |
Vendor: Unity Technologies
|
| 12 |
Begin MonoManager ReloadAssembly
|
| 13 |
+
- Completed reload, in 0.048 seconds
|
| 14 |
ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
| 15 |
ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
| 16 |
ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
|
|
|
| 35 |
WARNING: Shader Unsupported: 'Standard' - All subshaders removed
|
| 36 |
WARNING: Shader Did you use #pragma only_renderers and omit this platform?
|
| 37 |
WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
|
| 38 |
+
UnloadTime: 0.230292 ms
|
| 39 |
Registered Communicator in Agent.
|
| 40 |
ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
|
run_logs/timers.json
CHANGED
|
@@ -1,8 +1,310 @@
|
|
| 1 |
{
|
| 2 |
"name": "root",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"metadata": {
|
| 4 |
"timer_format_version": "0.1.0",
|
| 5 |
-
"start_time_seconds": "
|
| 6 |
"python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
|
| 7 |
"command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume --no-graphics",
|
| 8 |
"mlagents_version": "1.1.0.dev0",
|
|
@@ -10,103 +312,103 @@
|
|
| 10 |
"communication_protocol_version": "1.5.0",
|
| 11 |
"pytorch_version": "2.4.0",
|
| 12 |
"numpy_version": "1.23.5",
|
| 13 |
-
"end_time_seconds": "
|
| 14 |
},
|
| 15 |
-
"total":
|
| 16 |
"count": 1,
|
| 17 |
-
"self": 0.
|
| 18 |
"children": {
|
| 19 |
"run_training.setup": {
|
| 20 |
-
"total": 0.
|
| 21 |
"count": 1,
|
| 22 |
-
"self": 0.
|
| 23 |
},
|
| 24 |
"TrainerController.start_learning": {
|
| 25 |
-
"total":
|
| 26 |
"count": 1,
|
| 27 |
-
"self":
|
| 28 |
"children": {
|
| 29 |
"TrainerController._reset_env": {
|
| 30 |
-
"total": 3.
|
| 31 |
-
"count":
|
| 32 |
-
"self": 3.
|
| 33 |
},
|
| 34 |
"TrainerController.advance": {
|
| 35 |
-
"total":
|
| 36 |
-
"count":
|
| 37 |
-
"self":
|
| 38 |
"children": {
|
| 39 |
"env_step": {
|
| 40 |
-
"total":
|
| 41 |
-
"count":
|
| 42 |
-
"self":
|
| 43 |
"children": {
|
| 44 |
"SubprocessEnvManager._take_step": {
|
| 45 |
-
"total":
|
| 46 |
-
"count":
|
| 47 |
-
"self":
|
| 48 |
"children": {
|
| 49 |
"TorchPolicy.evaluate": {
|
| 50 |
-
"total":
|
| 51 |
-
"count":
|
| 52 |
-
"self":
|
| 53 |
}
|
| 54 |
}
|
| 55 |
},
|
| 56 |
"workers": {
|
| 57 |
-
"total": 0.
|
| 58 |
-
"count":
|
| 59 |
"self": 0.0,
|
| 60 |
"children": {
|
| 61 |
"worker_root": {
|
| 62 |
-
"total":
|
| 63 |
-
"count":
|
| 64 |
"is_parallel": true,
|
| 65 |
-
"self":
|
| 66 |
"children": {
|
| 67 |
"steps_from_proto": {
|
| 68 |
-
"total": 0.
|
| 69 |
-
"count":
|
| 70 |
"is_parallel": true,
|
| 71 |
-
"self": 0.
|
| 72 |
"children": {
|
| 73 |
"_process_rank_one_or_two_observation": {
|
| 74 |
-
"total": 0.
|
| 75 |
-
"count":
|
| 76 |
"is_parallel": true,
|
| 77 |
-
"self": 0.
|
| 78 |
}
|
| 79 |
}
|
| 80 |
},
|
| 81 |
"UnityEnvironment.step": {
|
| 82 |
-
"total":
|
| 83 |
-
"count":
|
| 84 |
"is_parallel": true,
|
| 85 |
-
"self":
|
| 86 |
"children": {
|
| 87 |
"UnityEnvironment._generate_step_input": {
|
| 88 |
-
"total":
|
| 89 |
-
"count":
|
| 90 |
"is_parallel": true,
|
| 91 |
-
"self":
|
| 92 |
},
|
| 93 |
"communicator.exchange": {
|
| 94 |
-
"total":
|
| 95 |
-
"count":
|
| 96 |
"is_parallel": true,
|
| 97 |
-
"self":
|
| 98 |
},
|
| 99 |
"steps_from_proto": {
|
| 100 |
-
"total":
|
| 101 |
-
"count":
|
| 102 |
"is_parallel": true,
|
| 103 |
-
"self":
|
| 104 |
"children": {
|
| 105 |
"_process_rank_one_or_two_observation": {
|
| 106 |
-
"total":
|
| 107 |
-
"count":
|
| 108 |
"is_parallel": true,
|
| 109 |
-
"self":
|
| 110 |
}
|
| 111 |
}
|
| 112 |
}
|
|
@@ -119,33 +421,52 @@
|
|
| 119 |
}
|
| 120 |
},
|
| 121 |
"trainer_advance": {
|
| 122 |
-
"total":
|
| 123 |
-
"count":
|
| 124 |
-
"self":
|
| 125 |
"children": {
|
| 126 |
"process_trajectory": {
|
| 127 |
-
"total":
|
| 128 |
-
"count":
|
| 129 |
-
"self":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
}
|
| 131 |
}
|
| 132 |
}
|
| 133 |
}
|
| 134 |
},
|
| 135 |
"trainer_threads": {
|
| 136 |
-
"total":
|
| 137 |
"count": 1,
|
| 138 |
-
"self":
|
| 139 |
},
|
| 140 |
"TrainerController._save_models": {
|
| 141 |
-
"total": 0.
|
| 142 |
"count": 1,
|
| 143 |
-
"self": 0.
|
| 144 |
"children": {
|
| 145 |
"RLTrainer._checkpoint": {
|
| 146 |
-
"total": 0.
|
| 147 |
"count": 1,
|
| 148 |
-
"self": 0.
|
| 149 |
}
|
| 150 |
}
|
| 151 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"name": "root",
|
| 3 |
+
"gauges": {
|
| 4 |
+
"SoccerTwos.Policy.Entropy.mean": {
|
| 5 |
+
"value": 2.1416494846343994,
|
| 6 |
+
"min": 2.0137786865234375,
|
| 7 |
+
"max": 2.151839017868042,
|
| 8 |
+
"count": 229
|
| 9 |
+
},
|
| 10 |
+
"SoccerTwos.Policy.Entropy.sum": {
|
| 11 |
+
"value": 41599.3984375,
|
| 12 |
+
"min": 27844.923828125,
|
| 13 |
+
"max": 47085.4375,
|
| 14 |
+
"count": 229
|
| 15 |
+
},
|
| 16 |
+
"SoccerTwos.Environment.EpisodeLength.mean": {
|
| 17 |
+
"value": 70.91304347826087,
|
| 18 |
+
"min": 50.824742268041234,
|
| 19 |
+
"max": 86.2280701754386,
|
| 20 |
+
"count": 229
|
| 21 |
+
},
|
| 22 |
+
"SoccerTwos.Environment.EpisodeLength.sum": {
|
| 23 |
+
"value": 19572.0,
|
| 24 |
+
"min": 11252.0,
|
| 25 |
+
"max": 21360.0,
|
| 26 |
+
"count": 229
|
| 27 |
+
},
|
| 28 |
+
"SoccerTwos.Self-play.ELO.mean": {
|
| 29 |
+
"value": 90.32114998486692,
|
| 30 |
+
"min": 67.98246219987821,
|
| 31 |
+
"max": 106.5567773055241,
|
| 32 |
+
"count": 229
|
| 33 |
+
},
|
| 34 |
+
"SoccerTwos.Self-play.ELO.sum": {
|
| 35 |
+
"value": 12464.318697911634,
|
| 36 |
+
"min": 7314.330712543377,
|
| 37 |
+
"max": 19099.755722564205,
|
| 38 |
+
"count": 229
|
| 39 |
+
},
|
| 40 |
+
"SoccerTwos.Step.mean": {
|
| 41 |
+
"value": 30899950.0,
|
| 42 |
+
"min": 28619966.0,
|
| 43 |
+
"max": 30899950.0,
|
| 44 |
+
"count": 229
|
| 45 |
+
},
|
| 46 |
+
"SoccerTwos.Step.sum": {
|
| 47 |
+
"value": 30899950.0,
|
| 48 |
+
"min": 28619966.0,
|
| 49 |
+
"max": 30899950.0,
|
| 50 |
+
"count": 229
|
| 51 |
+
},
|
| 52 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
| 53 |
+
"value": -0.04198051616549492,
|
| 54 |
+
"min": -0.12825024127960205,
|
| 55 |
+
"max": 0.05813853442668915,
|
| 56 |
+
"count": 229
|
| 57 |
+
},
|
| 58 |
+
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
| 59 |
+
"value": -5.79331111907959,
|
| 60 |
+
"min": -16.676513671875,
|
| 61 |
+
"max": 8.662641525268555,
|
| 62 |
+
"count": 229
|
| 63 |
+
},
|
| 64 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
| 65 |
+
"value": -0.04343034699559212,
|
| 66 |
+
"min": -0.12868726253509521,
|
| 67 |
+
"max": 0.057454075664281845,
|
| 68 |
+
"count": 229
|
| 69 |
+
},
|
| 70 |
+
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
| 71 |
+
"value": -5.993387699127197,
|
| 72 |
+
"min": -16.638057708740234,
|
| 73 |
+
"max": 8.560657501220703,
|
| 74 |
+
"count": 229
|
| 75 |
+
},
|
| 76 |
+
"SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
|
| 77 |
+
"value": 0.0024543115869164467,
|
| 78 |
+
"min": 0.00020709412638098001,
|
| 79 |
+
"max": 0.24234014749526978,
|
| 80 |
+
"count": 229
|
| 81 |
+
},
|
| 82 |
+
"SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
|
| 83 |
+
"value": 0.3386949896812439,
|
| 84 |
+
"min": 0.03044283762574196,
|
| 85 |
+
"max": 44.54613494873047,
|
| 86 |
+
"count": 229
|
| 87 |
+
},
|
| 88 |
+
"SoccerTwos.Policy.CuriosityValueEstimate.mean": {
|
| 89 |
+
"value": 0.002094687195494771,
|
| 90 |
+
"min": 0.0002014237834373489,
|
| 91 |
+
"max": 0.2422645092010498,
|
| 92 |
+
"count": 229
|
| 93 |
+
},
|
| 94 |
+
"SoccerTwos.Policy.CuriosityValueEstimate.sum": {
|
| 95 |
+
"value": 0.2890668213367462,
|
| 96 |
+
"min": 0.031623534858226776,
|
| 97 |
+
"max": 44.569114685058594,
|
| 98 |
+
"count": 229
|
| 99 |
+
},
|
| 100 |
+
"SoccerTwos.Policy.RndBaselineEstimate.mean": {
|
| 101 |
+
"value": 0.00014870119048282504,
|
| 102 |
+
"min": -0.00018489075591787696,
|
| 103 |
+
"max": 0.00017628517525736243,
|
| 104 |
+
"count": 229
|
| 105 |
+
},
|
| 106 |
+
"SoccerTwos.Policy.RndBaselineEstimate.sum": {
|
| 107 |
+
"value": 0.020520763471722603,
|
| 108 |
+
"min": -0.029478061944246292,
|
| 109 |
+
"max": 0.029439624398946762,
|
| 110 |
+
"count": 229
|
| 111 |
+
},
|
| 112 |
+
"SoccerTwos.Policy.RndValueEstimate.mean": {
|
| 113 |
+
"value": 0.00015831700875423849,
|
| 114 |
+
"min": -0.00018485976033844054,
|
| 115 |
+
"max": 0.0001771982351783663,
|
| 116 |
+
"count": 229
|
| 117 |
+
},
|
| 118 |
+
"SoccerTwos.Policy.RndValueEstimate.sum": {
|
| 119 |
+
"value": 0.021847747266292572,
|
| 120 |
+
"min": -0.029127497225999832,
|
| 121 |
+
"max": 0.029592106118798256,
|
| 122 |
+
"count": 229
|
| 123 |
+
},
|
| 124 |
+
"SoccerTwos.Environment.CumulativeReward.mean": {
|
| 125 |
+
"value": 0.0,
|
| 126 |
+
"min": 0.0,
|
| 127 |
+
"max": 0.0,
|
| 128 |
+
"count": 229
|
| 129 |
+
},
|
| 130 |
+
"SoccerTwos.Environment.CumulativeReward.sum": {
|
| 131 |
+
"value": 0.0,
|
| 132 |
+
"min": 0.0,
|
| 133 |
+
"max": 0.0,
|
| 134 |
+
"count": 229
|
| 135 |
+
},
|
| 136 |
+
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
| 137 |
+
"value": -0.04998840801957725,
|
| 138 |
+
"min": -0.4002886958744215,
|
| 139 |
+
"max": 0.2771585784720246,
|
| 140 |
+
"count": 229
|
| 141 |
+
},
|
| 142 |
+
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
| 143 |
+
"value": -6.89840030670166,
|
| 144 |
+
"min": -50.038799941539764,
|
| 145 |
+
"max": 46.839799761772156,
|
| 146 |
+
"count": 229
|
| 147 |
+
},
|
| 148 |
+
"SoccerTwos.Policy.CuriosityReward.mean": {
|
| 149 |
+
"value": 3.3735505580296747e-06,
|
| 150 |
+
"min": 0.0,
|
| 151 |
+
"max": 5.779475230838216e-06,
|
| 152 |
+
"count": 229
|
| 153 |
+
},
|
| 154 |
+
"SoccerTwos.Policy.CuriosityReward.sum": {
|
| 155 |
+
"value": 0.0004655499770080951,
|
| 156 |
+
"min": 0.0,
|
| 157 |
+
"max": 0.0008388239721170976,
|
| 158 |
+
"count": 229
|
| 159 |
+
},
|
| 160 |
+
"SoccerTwos.Policy.RndReward.mean": {
|
| 161 |
+
"value": 1.553490576139646e-06,
|
| 162 |
+
"min": 1.0619012450802476e-06,
|
| 163 |
+
"max": 1.9177394476529395e-06,
|
| 164 |
+
"count": 229
|
| 165 |
+
},
|
| 166 |
+
"SoccerTwos.Policy.RndReward.sum": {
|
| 167 |
+
"value": 0.00021438169950727115,
|
| 168 |
+
"min": 0.00013151309185133186,
|
| 169 |
+
"max": 0.00022558096927838278,
|
| 170 |
+
"count": 229
|
| 171 |
+
},
|
| 172 |
+
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
| 173 |
+
"value": -0.04998840801957725,
|
| 174 |
+
"min": -0.4002886958744215,
|
| 175 |
+
"max": 0.2771585784720246,
|
| 176 |
+
"count": 229
|
| 177 |
+
},
|
| 178 |
+
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
| 179 |
+
"value": -6.89840030670166,
|
| 180 |
+
"min": -50.038799941539764,
|
| 181 |
+
"max": 46.839799761772156,
|
| 182 |
+
"count": 229
|
| 183 |
+
},
|
| 184 |
+
"SoccerTwos.IsTraining.mean": {
|
| 185 |
+
"value": 1.0,
|
| 186 |
+
"min": 1.0,
|
| 187 |
+
"max": 1.0,
|
| 188 |
+
"count": 229
|
| 189 |
+
},
|
| 190 |
+
"SoccerTwos.IsTraining.sum": {
|
| 191 |
+
"value": 1.0,
|
| 192 |
+
"min": 1.0,
|
| 193 |
+
"max": 1.0,
|
| 194 |
+
"count": 229
|
| 195 |
+
},
|
| 196 |
+
"SoccerTwos.Losses.PolicyLoss.mean": {
|
| 197 |
+
"value": 0.011783653045616424,
|
| 198 |
+
"min": 0.0072254263698899495,
|
| 199 |
+
"max": 0.0510992972801129,
|
| 200 |
+
"count": 15
|
| 201 |
+
},
|
| 202 |
+
"SoccerTwos.Losses.PolicyLoss.sum": {
|
| 203 |
+
"value": 0.011783653045616424,
|
| 204 |
+
"min": 0.0072254263698899495,
|
| 205 |
+
"max": 0.0510992972801129,
|
| 206 |
+
"count": 15
|
| 207 |
+
},
|
| 208 |
+
"SoccerTwos.Losses.ValueLoss.mean": {
|
| 209 |
+
"value": 0.02236808432886998,
|
| 210 |
+
"min": 0.02193430345505476,
|
| 211 |
+
"max": 0.025202005325506132,
|
| 212 |
+
"count": 15
|
| 213 |
+
},
|
| 214 |
+
"SoccerTwos.Losses.ValueLoss.sum": {
|
| 215 |
+
"value": 0.02236808432886998,
|
| 216 |
+
"min": 0.02193430345505476,
|
| 217 |
+
"max": 0.025202005325506132,
|
| 218 |
+
"count": 15
|
| 219 |
+
},
|
| 220 |
+
"SoccerTwos.Losses.BaselineLoss.mean": {
|
| 221 |
+
"value": 0.02246675391991933,
|
| 222 |
+
"min": 0.02218010788783431,
|
| 223 |
+
"max": 0.025417460439105827,
|
| 224 |
+
"count": 15
|
| 225 |
+
},
|
| 226 |
+
"SoccerTwos.Losses.BaselineLoss.sum": {
|
| 227 |
+
"value": 0.02246675391991933,
|
| 228 |
+
"min": 0.02218010788783431,
|
| 229 |
+
"max": 0.025417460439105827,
|
| 230 |
+
"count": 15
|
| 231 |
+
},
|
| 232 |
+
"SoccerTwos.Policy.LearningRate.mean": {
|
| 233 |
+
"value": 0.0003,
|
| 234 |
+
"min": 0.0003,
|
| 235 |
+
"max": 0.0003,
|
| 236 |
+
"count": 15
|
| 237 |
+
},
|
| 238 |
+
"SoccerTwos.Policy.LearningRate.sum": {
|
| 239 |
+
"value": 0.0003,
|
| 240 |
+
"min": 0.0003,
|
| 241 |
+
"max": 0.0003,
|
| 242 |
+
"count": 15
|
| 243 |
+
},
|
| 244 |
+
"SoccerTwos.Policy.Epsilon.mean": {
|
| 245 |
+
"value": 0.20000000000000004,
|
| 246 |
+
"min": 0.20000000000000004,
|
| 247 |
+
"max": 0.20000000000000004,
|
| 248 |
+
"count": 15
|
| 249 |
+
},
|
| 250 |
+
"SoccerTwos.Policy.Epsilon.sum": {
|
| 251 |
+
"value": 0.20000000000000004,
|
| 252 |
+
"min": 0.20000000000000004,
|
| 253 |
+
"max": 0.20000000000000004,
|
| 254 |
+
"count": 15
|
| 255 |
+
},
|
| 256 |
+
"SoccerTwos.Policy.Beta.mean": {
|
| 257 |
+
"value": 0.006152085766,
|
| 258 |
+
"min": 0.006152085766,
|
| 259 |
+
"max": 0.00640850284225,
|
| 260 |
+
"count": 15
|
| 261 |
+
},
|
| 262 |
+
"SoccerTwos.Policy.Beta.sum": {
|
| 263 |
+
"value": 0.006152085766,
|
| 264 |
+
"min": 0.006152085766,
|
| 265 |
+
"max": 0.00640850284225,
|
| 266 |
+
"count": 15
|
| 267 |
+
},
|
| 268 |
+
"SoccerTwos.Losses.CuriosityForwardLoss.mean": {
|
| 269 |
+
"value": 0.044924141528705754,
|
| 270 |
+
"min": 0.044924141528705754,
|
| 271 |
+
"max": 0.12874181816975275,
|
| 272 |
+
"count": 15
|
| 273 |
+
},
|
| 274 |
+
"SoccerTwos.Losses.CuriosityForwardLoss.sum": {
|
| 275 |
+
"value": 0.044924141528705754,
|
| 276 |
+
"min": 0.044924141528705754,
|
| 277 |
+
"max": 0.12874181816975275,
|
| 278 |
+
"count": 15
|
| 279 |
+
},
|
| 280 |
+
"SoccerTwos.Losses.CuriosityInverseLoss.mean": {
|
| 281 |
+
"value": 1.5999893347422283,
|
| 282 |
+
"min": 1.5462068021297455,
|
| 283 |
+
"max": 1.7163931628068287,
|
| 284 |
+
"count": 15
|
| 285 |
+
},
|
| 286 |
+
"SoccerTwos.Losses.CuriosityInverseLoss.sum": {
|
| 287 |
+
"value": 1.5999893347422283,
|
| 288 |
+
"min": 1.5462068021297455,
|
| 289 |
+
"max": 1.7163931628068287,
|
| 290 |
+
"count": 15
|
| 291 |
+
},
|
| 292 |
+
"SoccerTwos.Losses.RNDLoss.mean": {
|
| 293 |
+
"value": 0.018670696765184402,
|
| 294 |
+
"min": 0.018668334931135178,
|
| 295 |
+
"max": 0.02088502235710621,
|
| 296 |
+
"count": 15
|
| 297 |
+
},
|
| 298 |
+
"SoccerTwos.Losses.RNDLoss.sum": {
|
| 299 |
+
"value": 0.018670696765184402,
|
| 300 |
+
"min": 0.018668334931135178,
|
| 301 |
+
"max": 0.02088502235710621,
|
| 302 |
+
"count": 15
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
"metadata": {
|
| 306 |
"timer_format_version": "0.1.0",
|
| 307 |
+
"start_time_seconds": "1725639262",
|
| 308 |
"python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
|
| 309 |
"command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/three.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --resume --no-graphics",
|
| 310 |
"mlagents_version": "1.1.0.dev0",
|
|
|
|
| 312 |
"communication_protocol_version": "1.5.0",
|
| 313 |
"pytorch_version": "2.4.0",
|
| 314 |
"numpy_version": "1.23.5",
|
| 315 |
+
"end_time_seconds": "1725648389"
|
| 316 |
},
|
| 317 |
+
"total": 9127.100674749992,
|
| 318 |
"count": 1,
|
| 319 |
+
"self": 0.15175625000847504,
|
| 320 |
"children": {
|
| 321 |
"run_training.setup": {
|
| 322 |
+
"total": 0.017048291978426278,
|
| 323 |
"count": 1,
|
| 324 |
+
"self": 0.017048291978426278
|
| 325 |
},
|
| 326 |
"TrainerController.start_learning": {
|
| 327 |
+
"total": 9126.931870208005,
|
| 328 |
"count": 1,
|
| 329 |
+
"self": 1.415727891610004,
|
| 330 |
"children": {
|
| 331 |
"TrainerController._reset_env": {
|
| 332 |
+
"total": 3.5643327069701627,
|
| 333 |
+
"count": 7,
|
| 334 |
+
"self": 3.5643327069701627
|
| 335 |
},
|
| 336 |
"TrainerController.advance": {
|
| 337 |
+
"total": 9121.758065358445,
|
| 338 |
+
"count": 158196,
|
| 339 |
+
"self": 1.3677141138759907,
|
| 340 |
"children": {
|
| 341 |
"env_step": {
|
| 342 |
+
"total": 6411.4115795473335,
|
| 343 |
+
"count": 158196,
|
| 344 |
+
"self": 6185.67660572668,
|
| 345 |
"children": {
|
| 346 |
"SubprocessEnvManager._take_step": {
|
| 347 |
+
"total": 224.9005823341431,
|
| 348 |
+
"count": 158196,
|
| 349 |
+
"self": 8.746982502460014,
|
| 350 |
"children": {
|
| 351 |
"TorchPolicy.evaluate": {
|
| 352 |
+
"total": 216.1535998316831,
|
| 353 |
+
"count": 287128,
|
| 354 |
+
"self": 216.1535998316831
|
| 355 |
}
|
| 356 |
}
|
| 357 |
},
|
| 358 |
"workers": {
|
| 359 |
+
"total": 0.8343914865108673,
|
| 360 |
+
"count": 158195,
|
| 361 |
"self": 0.0,
|
| 362 |
"children": {
|
| 363 |
"worker_root": {
|
| 364 |
+
"total": 9121.446049298218,
|
| 365 |
+
"count": 158195,
|
| 366 |
"is_parallel": true,
|
| 367 |
+
"self": 3101.727182136703,
|
| 368 |
"children": {
|
| 369 |
"steps_from_proto": {
|
| 370 |
+
"total": 0.009650043997680768,
|
| 371 |
+
"count": 14,
|
| 372 |
"is_parallel": true,
|
| 373 |
+
"self": 0.0012721649545710534,
|
| 374 |
"children": {
|
| 375 |
"_process_rank_one_or_two_observation": {
|
| 376 |
+
"total": 0.008377879043109715,
|
| 377 |
+
"count": 56,
|
| 378 |
"is_parallel": true,
|
| 379 |
+
"self": 0.008377879043109715
|
| 380 |
}
|
| 381 |
}
|
| 382 |
},
|
| 383 |
"UnityEnvironment.step": {
|
| 384 |
+
"total": 6019.709217117517,
|
| 385 |
+
"count": 158195,
|
| 386 |
"is_parallel": true,
|
| 387 |
+
"self": 15.64049137730035,
|
| 388 |
"children": {
|
| 389 |
"UnityEnvironment._generate_step_input": {
|
| 390 |
+
"total": 118.73067298045498,
|
| 391 |
+
"count": 158195,
|
| 392 |
"is_parallel": true,
|
| 393 |
+
"self": 118.73067298045498
|
| 394 |
},
|
| 395 |
"communicator.exchange": {
|
| 396 |
+
"total": 5690.6334428538685,
|
| 397 |
+
"count": 158195,
|
| 398 |
"is_parallel": true,
|
| 399 |
+
"self": 5690.6334428538685
|
| 400 |
},
|
| 401 |
"steps_from_proto": {
|
| 402 |
+
"total": 194.70460990589345,
|
| 403 |
+
"count": 316390,
|
| 404 |
"is_parallel": true,
|
| 405 |
+
"self": 23.100591495400295,
|
| 406 |
"children": {
|
| 407 |
"_process_rank_one_or_two_observation": {
|
| 408 |
+
"total": 171.60401841049315,
|
| 409 |
+
"count": 1265560,
|
| 410 |
"is_parallel": true,
|
| 411 |
+
"self": 171.60401841049315
|
| 412 |
}
|
| 413 |
}
|
| 414 |
}
|
|
|
|
| 421 |
}
|
| 422 |
},
|
| 423 |
"trainer_advance": {
|
| 424 |
+
"total": 2708.978771697235,
|
| 425 |
+
"count": 158195,
|
| 426 |
+
"self": 11.918968971876893,
|
| 427 |
"children": {
|
| 428 |
"process_trajectory": {
|
| 429 |
+
"total": 517.3845484333578,
|
| 430 |
+
"count": 158195,
|
| 431 |
+
"self": 516.6691328503366,
|
| 432 |
+
"children": {
|
| 433 |
+
"RLTrainer._checkpoint": {
|
| 434 |
+
"total": 0.7154155830212403,
|
| 435 |
+
"count": 4,
|
| 436 |
+
"self": 0.7154155830212403
|
| 437 |
+
}
|
| 438 |
+
}
|
| 439 |
+
},
|
| 440 |
+
"_update_policy": {
|
| 441 |
+
"total": 2179.6752542920003,
|
| 442 |
+
"count": 15,
|
| 443 |
+
"self": 212.8977203327231,
|
| 444 |
+
"children": {
|
| 445 |
+
"TorchPOCAOptimizer.update": {
|
| 446 |
+
"total": 1966.7775339592772,
|
| 447 |
+
"count": 180,
|
| 448 |
+
"self": 1966.7775339592772
|
| 449 |
+
}
|
| 450 |
+
}
|
| 451 |
}
|
| 452 |
}
|
| 453 |
}
|
| 454 |
}
|
| 455 |
},
|
| 456 |
"trainer_threads": {
|
| 457 |
+
"total": 4.5899651013314724e-07,
|
| 458 |
"count": 1,
|
| 459 |
+
"self": 4.5899651013314724e-07
|
| 460 |
},
|
| 461 |
"TrainerController._save_models": {
|
| 462 |
+
"total": 0.19374379198416136,
|
| 463 |
"count": 1,
|
| 464 |
+
"self": 0.0005647509824484587,
|
| 465 |
"children": {
|
| 466 |
"RLTrainer._checkpoint": {
|
| 467 |
+
"total": 0.1931790410017129,
|
| 468 |
"count": 1,
|
| 469 |
+
"self": 0.1931790410017129
|
| 470 |
}
|
| 471 |
}
|
| 472 |
}
|
run_logs/training_status.json
CHANGED
|
@@ -1,24 +1,24 @@
|
|
| 1 |
{
|
| 2 |
"SoccerTwos": {
|
| 3 |
-
"elo":
|
| 4 |
"checkpoints": [
|
| 5 |
{
|
| 6 |
-
"steps":
|
| 7 |
-
"file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-
|
| 8 |
"reward": 0.0,
|
| 9 |
-
"creation_time":
|
| 10 |
"auxillary_file_paths": [
|
| 11 |
-
"results/sept-run-01/SoccerTwos/SoccerTwos-
|
| 12 |
]
|
| 13 |
}
|
| 14 |
],
|
| 15 |
"final_checkpoint": {
|
| 16 |
-
"steps":
|
| 17 |
"file_path": "results/sept-run-01/SoccerTwos.onnx",
|
| 18 |
"reward": 0.0,
|
| 19 |
-
"creation_time":
|
| 20 |
"auxillary_file_paths": [
|
| 21 |
-
"results/sept-run-01/SoccerTwos/SoccerTwos-
|
| 22 |
]
|
| 23 |
}
|
| 24 |
},
|
|
|
|
| 1 |
{
|
| 2 |
"SoccerTwos": {
|
| 3 |
+
"elo": 90.32114998486692,
|
| 4 |
"checkpoints": [
|
| 5 |
{
|
| 6 |
+
"steps": 30907162,
|
| 7 |
+
"file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-30907162.onnx",
|
| 8 |
"reward": 0.0,
|
| 9 |
+
"creation_time": 1725648389.335208,
|
| 10 |
"auxillary_file_paths": [
|
| 11 |
+
"results/sept-run-01/SoccerTwos/SoccerTwos-30907162.pt"
|
| 12 |
]
|
| 13 |
}
|
| 14 |
],
|
| 15 |
"final_checkpoint": {
|
| 16 |
+
"steps": 30907162,
|
| 17 |
"file_path": "results/sept-run-01/SoccerTwos.onnx",
|
| 18 |
"reward": 0.0,
|
| 19 |
+
"creation_time": 1725648389.335208,
|
| 20 |
"auxillary_file_paths": [
|
| 21 |
+
"results/sept-run-01/SoccerTwos/SoccerTwos-30907162.pt"
|
| 22 |
]
|
| 23 |
}
|
| 24 |
},
|