Retraining old model
Browse files- SoccerTwos.onnx +1 -1
- config.json +1 -1
- configuration.yaml +7 -7
SoccerTwos.onnx
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1764633
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f22afbbe785d63813a768556c53b315402e13dd86bab0465b3ee10512605aced
|
3 |
size 1764633
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.
|
|
|
1 |
+
{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "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}}}, "init_path": "results/SoccerTwos/SoccerTwos/checkpoint.pt", "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-v2", "initialize_from": "SoccerTwos", "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
|
configuration.yaml
CHANGED
@@ -5,7 +5,7 @@ behaviors:
|
|
5 |
hyperparameters:
|
6 |
batch_size: 2048
|
7 |
buffer_size: 20480
|
8 |
-
learning_rate: 0.
|
9 |
beta: 0.005
|
10 |
epsilon: 0.2
|
11 |
lambd: 0.95
|
@@ -24,7 +24,7 @@ behaviors:
|
|
24 |
deterministic: false
|
25 |
reward_signals:
|
26 |
extrinsic:
|
27 |
-
gamma: 0.
|
28 |
strength: 1.0
|
29 |
network_settings:
|
30 |
normalize: false
|
@@ -34,7 +34,7 @@ behaviors:
|
|
34 |
memory: null
|
35 |
goal_conditioning_type: hyper
|
36 |
deterministic: false
|
37 |
-
init_path:
|
38 |
keep_checkpoints: 5
|
39 |
even_checkpoints: false
|
40 |
max_steps: 50000000
|
@@ -69,11 +69,11 @@ engine_settings:
|
|
69 |
no_graphics: true
|
70 |
environment_parameters: null
|
71 |
checkpoint_settings:
|
72 |
-
run_id: SoccerTwos
|
73 |
-
initialize_from:
|
74 |
load_model: false
|
75 |
-
resume:
|
76 |
-
force:
|
77 |
train_model: false
|
78 |
inference: false
|
79 |
results_dir: results
|
|
|
5 |
hyperparameters:
|
6 |
batch_size: 2048
|
7 |
buffer_size: 20480
|
8 |
+
learning_rate: 0.0001
|
9 |
beta: 0.005
|
10 |
epsilon: 0.2
|
11 |
lambd: 0.95
|
|
|
24 |
deterministic: false
|
25 |
reward_signals:
|
26 |
extrinsic:
|
27 |
+
gamma: 0.995
|
28 |
strength: 1.0
|
29 |
network_settings:
|
30 |
normalize: false
|
|
|
34 |
memory: null
|
35 |
goal_conditioning_type: hyper
|
36 |
deterministic: false
|
37 |
+
init_path: results/SoccerTwos/SoccerTwos/checkpoint.pt
|
38 |
keep_checkpoints: 5
|
39 |
even_checkpoints: false
|
40 |
max_steps: 50000000
|
|
|
69 |
no_graphics: true
|
70 |
environment_parameters: null
|
71 |
checkpoint_settings:
|
72 |
+
run_id: SoccerTwos-v2
|
73 |
+
initialize_from: SoccerTwos
|
74 |
load_model: false
|
75 |
+
resume: false
|
76 |
+
force: true
|
77 |
train_model: false
|
78 |
inference: false
|
79 |
results_dir: results
|