Initial commit
Browse files- .gitattributes +1 -0
- README.md +59 -0
- args.yml +65 -0
- config.yml +11 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- tqc-Hopper-v3.zip +3 -0
- tqc-Hopper-v3/_stable_baselines3_version +1 -0
- tqc-Hopper-v3/actor.optimizer.pth +3 -0
- tqc-Hopper-v3/critic.optimizer.pth +3 -0
- tqc-Hopper-v3/data +114 -0
- tqc-Hopper-v3/ent_coef_optimizer.pth +3 -0
- tqc-Hopper-v3/policy.pth +3 -0
- tqc-Hopper-v3/pytorch_variables.pth +3 -0
- tqc-Hopper-v3/system_info.txt +7 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Hopper-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TQC
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 3752.28 +/- 6.14
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: Hopper-v3
|
20 |
+
type: Hopper-v3
|
21 |
+
---
|
22 |
+
|
23 |
+
# **TQC** Agent playing **Hopper-v3**
|
24 |
+
This is a trained model of a **TQC** agent playing **Hopper-v3**
|
25 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
26 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
27 |
+
|
28 |
+
The RL Zoo is a training framework for Stable Baselines3
|
29 |
+
reinforcement learning agents,
|
30 |
+
with hyperparameter optimization and pre-trained agents included.
|
31 |
+
|
32 |
+
## Usage (with SB3 RL Zoo)
|
33 |
+
|
34 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
35 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
36 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
37 |
+
|
38 |
+
```
|
39 |
+
# Download model and save it into the logs/ folder
|
40 |
+
python -m utils.load_from_hub --algo tqc --env Hopper-v3 -orga sb3 -f logs/
|
41 |
+
python enjoy.py --algo tqc --env Hopper-v3 -f logs/
|
42 |
+
```
|
43 |
+
|
44 |
+
## Training (with the RL Zoo)
|
45 |
+
```
|
46 |
+
python train.py --algo tqc --env Hopper-v3 -f logs/
|
47 |
+
# Upload the model and generate video (when possible)
|
48 |
+
python -m utils.push_to_hub --algo tqc --env Hopper-v3 -f logs/ -orga sb3
|
49 |
+
```
|
50 |
+
|
51 |
+
## Hyperparameters
|
52 |
+
```python
|
53 |
+
OrderedDict([('learning_starts', 10000),
|
54 |
+
('n_timesteps', 1000000.0),
|
55 |
+
('policy', 'MlpPolicy'),
|
56 |
+
('top_quantiles_to_drop_per_net', 5),
|
57 |
+
('use_sde', False),
|
58 |
+
('normalize', False)])
|
59 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- tqc
|
4 |
+
- - env
|
5 |
+
- Hopper-v3
|
6 |
+
- - env_kwargs
|
7 |
+
- null
|
8 |
+
- - eval_episodes
|
9 |
+
- 20
|
10 |
+
- - eval_freq
|
11 |
+
- 10000
|
12 |
+
- - gym_packages
|
13 |
+
- []
|
14 |
+
- - hyperparams
|
15 |
+
- use_sde: false
|
16 |
+
- - log_folder
|
17 |
+
- logs/
|
18 |
+
- - log_interval
|
19 |
+
- 10
|
20 |
+
- - n_eval_envs
|
21 |
+
- 5
|
22 |
+
- - n_evaluations
|
23 |
+
- 20
|
24 |
+
- - n_jobs
|
25 |
+
- 1
|
26 |
+
- - n_startup_trials
|
27 |
+
- 10
|
28 |
+
- - n_timesteps
|
29 |
+
- 1000000
|
30 |
+
- - n_trials
|
31 |
+
- 10
|
32 |
+
- - no_optim_plots
|
33 |
+
- false
|
34 |
+
- - num_threads
|
35 |
+
- 2
|
36 |
+
- - optimization_log_path
|
37 |
+
- null
|
38 |
+
- - optimize_hyperparameters
|
39 |
+
- false
|
40 |
+
- - pruner
|
41 |
+
- median
|
42 |
+
- - sampler
|
43 |
+
- tpe
|
44 |
+
- - save_freq
|
45 |
+
- -1
|
46 |
+
- - save_replay_buffer
|
47 |
+
- false
|
48 |
+
- - seed
|
49 |
+
- 594371
|
50 |
+
- - storage
|
51 |
+
- null
|
52 |
+
- - study_name
|
53 |
+
- null
|
54 |
+
- - tensorboard_log
|
55 |
+
- ''
|
56 |
+
- - trained_agent
|
57 |
+
- ''
|
58 |
+
- - truncate_last_trajectory
|
59 |
+
- true
|
60 |
+
- - uuid
|
61 |
+
- true
|
62 |
+
- - vec_env
|
63 |
+
- dummy
|
64 |
+
- - verbose
|
65 |
+
- 1
|
config.yml
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - learning_starts
|
3 |
+
- 10000
|
4 |
+
- - n_timesteps
|
5 |
+
- 1000000.0
|
6 |
+
- - policy
|
7 |
+
- MlpPolicy
|
8 |
+
- - top_quantiles_to_drop_per_net
|
9 |
+
- 5
|
10 |
+
- - use_sde
|
11 |
+
- false
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03b310651ec366c1e0d429e24a9192507c29795c307586f1781a2d78bc3255fb
|
3 |
+
size 1674684
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 3752.2834491999993, "std_reward": 6.142125240643728, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T20:55:13.538690"}
|
tqc-Hopper-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3df17b8895115cb941827aa8387fd8e520ad233c6490b565e754cb03c973f005
|
3 |
+
size 3322726
|
tqc-Hopper-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.1a8
|
tqc-Hopper-v3/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e971e03438a14bf086bb2a87e081dafb72364081d954ac3a8146afe1883519e
|
3 |
+
size 567605
|
tqc-Hopper-v3/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9fbf5e40931b5e7cda721116b1c297016b8a2f9d6da4708e6858b3ac1c48759
|
3 |
+
size 1223325
|
tqc-Hopper-v3/data
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "sb3_contrib.tqc.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TQC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the feature extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_quantiles: Number of quantiles for the critic.\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
7 |
+
"__init__": "<function TQCPolicy.__init__ at 0x7f3c32a69710>",
|
8 |
+
"_build": "<function TQCPolicy._build at 0x7f3c32a697a0>",
|
9 |
+
"_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7f3c32a69830>",
|
10 |
+
"reset_noise": "<function TQCPolicy.reset_noise at 0x7f3c32a698c0>",
|
11 |
+
"make_actor": "<function TQCPolicy.make_actor at 0x7f3c32a69950>",
|
12 |
+
"make_critic": "<function TQCPolicy.make_critic at 0x7f3c32a699e0>",
|
13 |
+
"forward": "<function TQCPolicy.forward at 0x7f3c32a69a70>",
|
14 |
+
"_predict": "<function TQCPolicy._predict at 0x7f3c32a69b00>",
|
15 |
+
"set_training_mode": "<function TQCPolicy.set_training_mode at 0x7f3c32a69b90>",
|
16 |
+
"__abstractmethods__": "frozenset()",
|
17 |
+
"_abc_impl": "<_abc_data object at 0x7f3c32ac8690>"
|
18 |
+
},
|
19 |
+
"verbose": 1,
|
20 |
+
"policy_kwargs": {
|
21 |
+
"use_sde": false
|
22 |
+
},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float64",
|
27 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
|
28 |
+
"high": "[inf inf inf inf inf inf inf inf inf inf inf]",
|
29 |
+
"bounded_below": "[False False False False False False False False False False False]",
|
30 |
+
"bounded_above": "[False False False False False False False False False False False]",
|
31 |
+
"_np_random": null,
|
32 |
+
"_shape": [
|
33 |
+
11
|
34 |
+
]
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
38 |
+
":serialized:": "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",
|
39 |
+
"dtype": "float32",
|
40 |
+
"low": "[-1. -1. -1.]",
|
41 |
+
"high": "[1. 1. 1.]",
|
42 |
+
"bounded_below": "[ True True True]",
|
43 |
+
"bounded_above": "[ True True True]",
|
44 |
+
"_np_random": "RandomState(MT19937)",
|
45 |
+
"_shape": [
|
46 |
+
3
|
47 |
+
]
|
48 |
+
},
|
49 |
+
"n_envs": 1,
|
50 |
+
"num_timesteps": 1000000,
|
51 |
+
"_total_timesteps": 1000000,
|
52 |
+
"_num_timesteps_at_start": 0,
|
53 |
+
"seed": 0,
|
54 |
+
"action_noise": null,
|
55 |
+
"start_time": 1635497702.9823372,
|
56 |
+
"learning_rate": 0.0003,
|
57 |
+
"tensorboard_log": null,
|
58 |
+
"lr_schedule": {
|
59 |
+
":type:": "<class 'function'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_obs": null,
|
63 |
+
"_last_episode_starts": {
|
64 |
+
":type:": "<class 'numpy.ndarray'>",
|
65 |
+
":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
|
66 |
+
},
|
67 |
+
"_last_original_obs": {
|
68 |
+
":type:": "<class 'numpy.ndarray'>",
|
69 |
+
":serialized:": "gASV4gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLC4aUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNYLMQfFYei+j/ml/nFwDKlP+u5jCoRirW/IGwbpJCJ3b+28+QEWYuVv90R2iqrEgtAWJyK/+818D/qu0abQIv5P8eAjz4BNOa/Iv4zEkDhE0CZN0QIq9seQJR0lGIu"
|
70 |
+
},
|
71 |
+
"_episode_num": 2331,
|
72 |
+
"use_sde": false,
|
73 |
+
"sde_sample_freq": -1,
|
74 |
+
"_current_progress_remaining": 0.0,
|
75 |
+
"ep_info_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "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"
|
78 |
+
},
|
79 |
+
"ep_success_buffer": {
|
80 |
+
":type:": "<class 'collections.deque'>",
|
81 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
82 |
+
},
|
83 |
+
"_n_updates": 990000,
|
84 |
+
"buffer_size": 1,
|
85 |
+
"batch_size": 256,
|
86 |
+
"learning_starts": 10000,
|
87 |
+
"tau": 0.005,
|
88 |
+
"gamma": 0.99,
|
89 |
+
"gradient_steps": 1,
|
90 |
+
"optimize_memory_usage": false,
|
91 |
+
"replay_buffer_class": {
|
92 |
+
":type:": "<class 'abc.ABCMeta'>",
|
93 |
+
":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
94 |
+
"__module__": "stable_baselines3.common.buffers",
|
95 |
+
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device:\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
96 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7f3c33242b90>",
|
97 |
+
"add": "<function ReplayBuffer.add at 0x7f3c33242c20>",
|
98 |
+
"sample": "<function ReplayBuffer.sample at 0x7f3c32da97a0>",
|
99 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7f3c32da9830>",
|
100 |
+
"__abstractmethods__": "frozenset()",
|
101 |
+
"_abc_impl": "<_abc_data object at 0x7f3c3329a5d0>"
|
102 |
+
},
|
103 |
+
"replay_buffer_kwargs": {},
|
104 |
+
"train_freq": {
|
105 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
106 |
+
":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
107 |
+
},
|
108 |
+
"use_sde_at_warmup": false,
|
109 |
+
"target_entropy": -3.0,
|
110 |
+
"ent_coef": "auto",
|
111 |
+
"target_update_interval": 1,
|
112 |
+
"top_quantiles_to_drop_per_net": 5,
|
113 |
+
"remove_time_limit_termination": false
|
114 |
+
}
|
tqc-Hopper-v3/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:955b4dd4e893560662d5baad92986fc209b39e995c749daba8ff277ab4908fb4
|
3 |
+
size 1255
|
tqc-Hopper-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2d19e66dcdb6849388304e8e6fd7f5bb8cf90faf9420a8e8414d65440ec25d3
|
3 |
+
size 1509381
|
tqc-Hopper-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41f1bd1f3510ddebf977be0143b7fa3c82c1bef340ed8cb09fb92f7efda764a7
|
3 |
+
size 747
|
tqc-Hopper-v3/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
|
2 |
+
Python: 3.7.10
|
3 |
+
Stable-Baselines3: 1.5.1a8
|
4 |
+
PyTorch: 1.11.0
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.2
|
7 |
+
Gym: 0.21.0
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c57a456b2d63fa8d344e5885c8c4e568c92af20f8d464caffdfed1a6cd95a192
|
3 |
+
size 97434
|