Initial commit
Browse files- README.md +4 -4
- args.yml +5 -9
- config.yml +3 -3
- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
@@ -62,15 +62,15 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
|
|
62 |
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
-
OrderedDict([('batch_size',
|
66 |
-
('buffer_size',
|
67 |
('env_wrapper',
|
68 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
69 |
('exploration_final_eps', 0.01),
|
70 |
('exploration_fraction', 0.1),
|
71 |
('frame_stack', 4),
|
72 |
('gradient_steps', 1),
|
73 |
-
('learning_rate',
|
74 |
('learning_starts', 100000),
|
75 |
('n_timesteps', 10000000.0),
|
76 |
('optimize_memory_usage', False),
|
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 794.00 +/- 247.23
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
62 |
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
+
OrderedDict([('batch_size', 32),
|
66 |
+
('buffer_size', 100000),
|
67 |
('env_wrapper',
|
68 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
69 |
('exploration_final_eps', 0.01),
|
70 |
('exploration_fraction', 0.1),
|
71 |
('frame_stack', 4),
|
72 |
('gradient_steps', 1),
|
73 |
+
('learning_rate', 0.0001),
|
74 |
('learning_starts', 100000),
|
75 |
('n_timesteps', 10000000.0),
|
76 |
('optimize_memory_usage', False),
|
args.yml
CHANGED
@@ -1,8 +1,6 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - algo
|
3 |
- dqn
|
4 |
-
- - batch_size
|
5 |
-
- -1
|
6 |
- - conf_file
|
7 |
- null
|
8 |
- - device
|
@@ -18,9 +16,7 @@
|
|
18 |
- - gym_packages
|
19 |
- []
|
20 |
- - hyperparams
|
21 |
-
-
|
22 |
-
buffer_size: 150000
|
23 |
-
learning_rate: 5.0e-05
|
24 |
- - log_folder
|
25 |
- logs/
|
26 |
- - log_interval
|
@@ -36,7 +32,7 @@
|
|
36 |
- - n_startup_trials
|
37 |
- 10
|
38 |
- - n_timesteps
|
39 |
-
-
|
40 |
- - n_trials
|
41 |
- 500
|
42 |
- - no_optim_plots
|
@@ -54,11 +50,11 @@
|
|
54 |
- - sampler
|
55 |
- tpe
|
56 |
- - save_freq
|
57 |
-
-
|
58 |
- - save_replay_buffer
|
59 |
- false
|
60 |
- - seed
|
61 |
-
-
|
62 |
- - storage
|
63 |
- null
|
64 |
- - study_name
|
@@ -68,7 +64,7 @@
|
|
68 |
- - track
|
69 |
- false
|
70 |
- - trained_agent
|
71 |
-
-
|
72 |
- - truncate_last_trajectory
|
73 |
- true
|
74 |
- - uuid
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - algo
|
3 |
- dqn
|
|
|
|
|
4 |
- - conf_file
|
5 |
- null
|
6 |
- - device
|
|
|
16 |
- - gym_packages
|
17 |
- []
|
18 |
- - hyperparams
|
19 |
+
- null
|
|
|
|
|
20 |
- - log_folder
|
21 |
- logs/
|
22 |
- - log_interval
|
|
|
32 |
- - n_startup_trials
|
33 |
- 10
|
34 |
- - n_timesteps
|
35 |
+
- 1000000
|
36 |
- - n_trials
|
37 |
- 500
|
38 |
- - no_optim_plots
|
|
|
50 |
- - sampler
|
51 |
- tpe
|
52 |
- - save_freq
|
53 |
+
- 100000
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 3242211519
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
64 |
- - track
|
65 |
- false
|
66 |
- - trained_agent
|
67 |
+
- ''
|
68 |
- - truncate_last_trajectory
|
69 |
- true
|
70 |
- - uuid
|
config.yml
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - batch_size
|
3 |
-
-
|
4 |
- - buffer_size
|
5 |
-
-
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
- - exploration_final_eps
|
@@ -14,7 +14,7 @@
|
|
14 |
- - gradient_steps
|
15 |
- 1
|
16 |
- - learning_rate
|
17 |
-
-
|
18 |
- - learning_starts
|
19 |
- 100000
|
20 |
- - n_timesteps
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - batch_size
|
3 |
+
- 32
|
4 |
- - buffer_size
|
5 |
+
- 100000
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
- - exploration_final_eps
|
|
|
14 |
- - gradient_steps
|
15 |
- 1
|
16 |
- - learning_rate
|
17 |
+
- 0.0001
|
18 |
- - learning_starts
|
19 |
- 100000
|
20 |
- - n_timesteps
|
dqn-SpaceInvadersNoFrameskip-v4.zip
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 sha256:55b69fa4ef2376298d2ce01ce3cfa5ca048da8ff47e53c9e2022a92b16679a5a
|
3 |
+
size 27224807
|
dqn-SpaceInvadersNoFrameskip-v4/data
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13505739
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a6edc7dc842a574379bede3a7fb4d41843b86641b9248d95b19cf959cc92aa0
|
3 |
size 13505739
|
dqn-SpaceInvadersNoFrameskip-v4/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13504937
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5884d000da089a1d98d2f9284741a6ac57d52037035966483b1dc0f7ebebbc61
|
3 |
size 13504937
|
replay.mp4
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 sha256:3e41ea531f1520c05a66684eec10c00f10517eb05cfa19ef4beda5810799ae6e
|
3 |
+
size 239758
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 794.0, "std_reward": 247.2326839234651, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-21T03:08:41.705194"}
|
train_eval_metrics.zip
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 sha256:14d915c56248fdebdce8c0310d15a3aa0f7c7ba9cfecb6f43cb35f65efbb59a9
|
3 |
+
size 37873
|