CoreyMorris
commited on
Commit
•
b0047db
1
Parent(s):
94ebb7f
Adjusting learning rate
Browse files- README.md +3 -3
- args.yml +5 -5
- config.yml +2 -2
- replay.mp4 +2 -2
- results.json +1 -1
- tqc-PandaReachDense-v2.zip +2 -2
- tqc-PandaReachDense-v2/actor.optimizer.pth +1 -1
- tqc-PandaReachDense-v2/critic.optimizer.pth +1 -1
- tqc-PandaReachDense-v2/data +33 -33
- tqc-PandaReachDense-v2/ent_coef_optimizer.pth +1 -1
- tqc-PandaReachDense-v2/policy.pth +1 -1
- tqc-PandaReachDense-v2/pytorch_variables.pth +1 -1
- train_eval_metrics.zip +2 -2
- vec_normalize.pkl +2 -2
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: PandaReachDense-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value: -0.
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
@@ -67,9 +67,9 @@ OrderedDict([('batch_size', 256),
|
|
67 |
('ent_coef', 'auto'),
|
68 |
('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
|
69 |
('gamma', 0.95),
|
70 |
-
('learning_rate',
|
71 |
('learning_starts', 1000),
|
72 |
-
('n_timesteps',
|
73 |
('normalize', True),
|
74 |
('policy', 'MultiInputPolicy'),
|
75 |
('policy_kwargs', 'dict(net_arch=[64, 64], n_critics=1)'),
|
|
|
16 |
type: PandaReachDense-v2
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: -0.26 +/- 0.10
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
67 |
('ent_coef', 'auto'),
|
68 |
('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
|
69 |
('gamma', 0.95),
|
70 |
+
('learning_rate', 'lin_0.001'),
|
71 |
('learning_starts', 1000),
|
72 |
+
('n_timesteps', 100000.0),
|
73 |
('normalize', True),
|
74 |
('policy', 'MultiInputPolicy'),
|
75 |
('policy_kwargs', 'dict(net_arch=[64, 64], n_critics=1)'),
|
args.yml
CHANGED
@@ -12,7 +12,7 @@
|
|
12 |
- - eval_episodes
|
13 |
- 10
|
14 |
- - eval_freq
|
15 |
-
-
|
16 |
- - gym_packages
|
17 |
- []
|
18 |
- - hyperparams
|
@@ -50,21 +50,21 @@
|
|
50 |
- - sampler
|
51 |
- tpe
|
52 |
- - save_freq
|
53 |
-
-
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
61 |
- null
|
62 |
- - tensorboard_log
|
63 |
-
- runs/PandaReachDense-
|
64 |
- - track
|
65 |
- true
|
66 |
- - trained_agent
|
67 |
-
-
|
68 |
- - truncate_last_trajectory
|
69 |
- true
|
70 |
- - uuid
|
|
|
12 |
- - eval_episodes
|
13 |
- 10
|
14 |
- - eval_freq
|
15 |
+
- 10000
|
16 |
- - gym_packages
|
17 |
- []
|
18 |
- - hyperparams
|
|
|
50 |
- - sampler
|
51 |
- tpe
|
52 |
- - save_freq
|
53 |
+
- 10000
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 3534296952
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
61 |
- null
|
62 |
- - tensorboard_log
|
63 |
+
- runs/PandaReachDense-v2__tqc__3534296952__1674446910
|
64 |
- - track
|
65 |
- true
|
66 |
- - trained_agent
|
67 |
+
- logs/tqc/PandaReachDense-v2_2/rl_model_700000_steps.zip
|
68 |
- - truncate_last_trajectory
|
69 |
- true
|
70 |
- - uuid
|
config.yml
CHANGED
@@ -10,11 +10,11 @@
|
|
10 |
- - gamma
|
11 |
- 0.95
|
12 |
- - learning_rate
|
13 |
-
-
|
14 |
- - learning_starts
|
15 |
- 1000
|
16 |
- - n_timesteps
|
17 |
-
-
|
18 |
- - normalize
|
19 |
- true
|
20 |
- - policy
|
|
|
10 |
- - gamma
|
11 |
- 0.95
|
12 |
- - learning_rate
|
13 |
+
- lin_0.001
|
14 |
- - learning_starts
|
15 |
- 1000
|
16 |
- - n_timesteps
|
17 |
+
- 100000.0
|
18 |
- - normalize
|
19 |
- true
|
20 |
- - policy
|
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 sha256:8b2a49d0855a7cc559f3daec1f5b13daa2a92b58aac40016f3a872c924e1124b
|
3 |
+
size 342880
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward": -0.
|
|
|
1 |
+
{"mean_reward": -0.25831370000000003, "std_reward": 0.10294616297565441, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-22T23:45:08.927580"}
|
tqc-PandaReachDense-v2.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:d969ab4915853089b74a79650aaed2e3e89e04861a7c459c8948a4ec9c43ed3f
|
3 |
+
size 228199
|
tqc-PandaReachDense-v2/actor.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50077
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a99ed2795150e108b5c32ca83b098f16590c2a25f2d2247b423802a794d1a52
|
3 |
size 50077
|
tqc-PandaReachDense-v2/critic.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 59951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6be79d221b2634d077658dc7b13fec76f8ba575da9d23ec9cb13022b900e089
|
3 |
size 59951
|
tqc-PandaReachDense-v2/data
CHANGED
@@ -4,9 +4,9 @@
|
|
4 |
":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
|
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 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 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 MultiInputPolicy.__init__ at
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
-
"_abc_impl": "<_abc_data object at
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {
|
@@ -39,20 +39,20 @@
|
|
39 |
"_np_random": "RandomState(MT19937)"
|
40 |
},
|
41 |
"n_envs": 1,
|
42 |
-
"num_timesteps":
|
43 |
-
"_total_timesteps":
|
44 |
"_num_timesteps_at_start": 0,
|
45 |
"seed": 0,
|
46 |
"action_noise": null,
|
47 |
-
"start_time":
|
48 |
"learning_rate": {
|
49 |
":type:": "<class 'function'>",
|
50 |
-
":serialized:": "
|
51 |
},
|
52 |
-
"tensorboard_log": "runs/PandaReachDense-
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
-
":serialized:": "
|
56 |
},
|
57 |
"_last_obs": null,
|
58 |
"_last_episode_starts": {
|
@@ -61,24 +61,24 @@
|
|
61 |
},
|
62 |
"_last_original_obs": {
|
63 |
":type:": "<class 'collections.OrderedDict'>",
|
64 |
-
":serialized:": "
|
65 |
-
"achieved_goal": "[[-
|
66 |
-
"desired_goal": "[[
|
67 |
-
"observation": "[[-
|
68 |
},
|
69 |
-
"_episode_num":
|
70 |
"use_sde": false,
|
71 |
"sde_sample_freq": -1,
|
72 |
-
"_current_progress_remaining": 0.
|
73 |
"ep_info_buffer": {
|
74 |
":type:": "<class 'collections.deque'>",
|
75 |
-
":serialized:": "gAWV7xwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
76 |
},
|
77 |
"ep_success_buffer": {
|
78 |
":type:": "<class 'collections.deque'>",
|
79 |
":serialized:": "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"
|
80 |
},
|
81 |
-
"_n_updates":
|
82 |
"buffer_size": 1,
|
83 |
"batch_size": 256,
|
84 |
"learning_starts": 1000,
|
@@ -91,24 +91,24 @@
|
|
91 |
":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
|
92 |
"__module__": "stable_baselines3.her.her_replay_buffer",
|
93 |
"__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n .. warning::\n\n For performance reasons, the maximum number of steps per episodes must be specified.\n In most cases, it will be inferred if you specify ``max_episode_steps`` when registering the environment\n or if you use a ``gym.wrappers.TimeLimit`` (and ``env.spec`` is not None).\n Otherwise, you can directly pass ``max_episode_length`` to the replay buffer constructor.\n\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n In the online sampling case, these new transitions will not be saved in the replay buffer\n and will only be created at sampling time.\n\n :param env: The training environment\n :param buffer_size: The size of the buffer measured in transitions.\n :param max_episode_length: The maximum length of an episode. If not specified,\n it will be automatically inferred if the environment uses a ``gym.wrappers.TimeLimit`` wrapper.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param device: PyTorch device\n :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\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 ",
|
94 |
-
"__init__": "<function HerReplayBuffer.__init__ at
|
95 |
-
"__getstate__": "<function HerReplayBuffer.__getstate__ at
|
96 |
-
"__setstate__": "<function HerReplayBuffer.__setstate__ at
|
97 |
-
"set_env": "<function HerReplayBuffer.set_env at
|
98 |
-
"_get_samples": "<function HerReplayBuffer._get_samples at
|
99 |
-
"sample": "<function HerReplayBuffer.sample at
|
100 |
-
"_sample_offline": "<function HerReplayBuffer._sample_offline at
|
101 |
-
"sample_goals": "<function HerReplayBuffer.sample_goals at
|
102 |
-
"_sample_transitions": "<function HerReplayBuffer._sample_transitions at
|
103 |
-
"add": "<function HerReplayBuffer.add at
|
104 |
-
"store_episode": "<function HerReplayBuffer.store_episode at
|
105 |
-
"_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at
|
106 |
-
"n_episodes_stored": "<property object at
|
107 |
-
"size": "<function HerReplayBuffer.size at
|
108 |
-
"reset": "<function HerReplayBuffer.reset at
|
109 |
-
"truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at
|
110 |
"__abstractmethods__": "frozenset()",
|
111 |
-
"_abc_impl": "<_abc_data object at
|
112 |
},
|
113 |
"replay_buffer_kwargs": {
|
114 |
"online_sampling": true,
|
|
|
4 |
":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
|
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 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 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 MultiInputPolicy.__init__ at 0x7f11674de280>",
|
8 |
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc_data object at 0x7f11674d9720>"
|
10 |
},
|
11 |
"verbose": 1,
|
12 |
"policy_kwargs": {
|
|
|
39 |
"_np_random": "RandomState(MT19937)"
|
40 |
},
|
41 |
"n_envs": 1,
|
42 |
+
"num_timesteps": 100000,
|
43 |
+
"_total_timesteps": 100000,
|
44 |
"_num_timesteps_at_start": 0,
|
45 |
"seed": 0,
|
46 |
"action_noise": null,
|
47 |
+
"start_time": 1674446919094715484,
|
48 |
"learning_rate": {
|
49 |
":type:": "<class 'function'>",
|
50 |
+
":serialized:": "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"
|
51 |
},
|
52 |
+
"tensorboard_log": "runs/PandaReachDense-v2__tqc__3534296952__1674446910/PandaReachDense-v2",
|
53 |
"lr_schedule": {
|
54 |
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
},
|
57 |
"_last_obs": null,
|
58 |
"_last_episode_starts": {
|
|
|
61 |
},
|
62 |
"_last_original_obs": {
|
63 |
":type:": "<class 'collections.OrderedDict'>",
|
64 |
+
":serialized:": "gAWVLwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAEtXhPYa9nj25kIA+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWHAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAAAIA/lGgOSwFLB4aUaBJ0lFKUdS4=",
|
65 |
+
"achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
|
66 |
+
"desired_goal": "[[0.11026968 0.07750992 0.25110415]]",
|
67 |
+
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 1.0000000e+00]]"
|
68 |
},
|
69 |
+
"_episode_num": 2000,
|
70 |
"use_sde": false,
|
71 |
"sde_sample_freq": -1,
|
72 |
+
"_current_progress_remaining": 0.0,
|
73 |
"ep_info_buffer": {
|
74 |
":type:": "<class 'collections.deque'>",
|
75 |
+
":serialized:": "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"
|
76 |
},
|
77 |
"ep_success_buffer": {
|
78 |
":type:": "<class 'collections.deque'>",
|
79 |
":serialized:": "gAWVMwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolggAAAAAAAAAAAAAAAAA8D+UjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiKYwBQ5R0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUaAcolggAAAAAAAAAAAAAAAAA8D+UaA4paBF0lFKUZS4="
|
80 |
},
|
81 |
+
"_n_updates": 797999,
|
82 |
"buffer_size": 1,
|
83 |
"batch_size": 256,
|
84 |
"learning_starts": 1000,
|
|
|
91 |
":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
|
92 |
"__module__": "stable_baselines3.her.her_replay_buffer",
|
93 |
"__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n .. warning::\n\n For performance reasons, the maximum number of steps per episodes must be specified.\n In most cases, it will be inferred if you specify ``max_episode_steps`` when registering the environment\n or if you use a ``gym.wrappers.TimeLimit`` (and ``env.spec`` is not None).\n Otherwise, you can directly pass ``max_episode_length`` to the replay buffer constructor.\n\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n In the online sampling case, these new transitions will not be saved in the replay buffer\n and will only be created at sampling time.\n\n :param env: The training environment\n :param buffer_size: The size of the buffer measured in transitions.\n :param max_episode_length: The maximum length of an episode. If not specified,\n it will be automatically inferred if the environment uses a ``gym.wrappers.TimeLimit`` wrapper.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param device: PyTorch device\n :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\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 ",
|
94 |
+
"__init__": "<function HerReplayBuffer.__init__ at 0x7f11679829d0>",
|
95 |
+
"__getstate__": "<function HerReplayBuffer.__getstate__ at 0x7f1167982a60>",
|
96 |
+
"__setstate__": "<function HerReplayBuffer.__setstate__ at 0x7f1167982af0>",
|
97 |
+
"set_env": "<function HerReplayBuffer.set_env at 0x7f1167982b80>",
|
98 |
+
"_get_samples": "<function HerReplayBuffer._get_samples at 0x7f1167982c10>",
|
99 |
+
"sample": "<function HerReplayBuffer.sample at 0x7f1167982ca0>",
|
100 |
+
"_sample_offline": "<function HerReplayBuffer._sample_offline at 0x7f1167982d30>",
|
101 |
+
"sample_goals": "<function HerReplayBuffer.sample_goals at 0x7f1167982dc0>",
|
102 |
+
"_sample_transitions": "<function HerReplayBuffer._sample_transitions at 0x7f1167982e50>",
|
103 |
+
"add": "<function HerReplayBuffer.add at 0x7f1167982ee0>",
|
104 |
+
"store_episode": "<function HerReplayBuffer.store_episode at 0x7f1167982f70>",
|
105 |
+
"_sample_her_transitions": "<function HerReplayBuffer._sample_her_transitions at 0x7f1167995040>",
|
106 |
+
"n_episodes_stored": "<property object at 0x7f11679915e0>",
|
107 |
+
"size": "<function HerReplayBuffer.size at 0x7f1167995160>",
|
108 |
+
"reset": "<function HerReplayBuffer.reset at 0x7f11679951f0>",
|
109 |
+
"truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x7f1167995280>",
|
110 |
"__abstractmethods__": "frozenset()",
|
111 |
+
"_abc_impl": "<_abc_data object at 0x7f1167990210>"
|
112 |
},
|
113 |
"replay_buffer_kwargs": {
|
114 |
"online_sampling": true,
|
tqc-PandaReachDense-v2/ent_coef_optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1507
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b5a352137f37c10db6a00c733350bff417a03e6b202261435d573e68ff7fc4
|
3 |
size 1507
|
tqc-PandaReachDense-v2/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fb990b684ce56a3f5c93d613f378afa2a3ba0e7cd46508386a5d11686aad280
|
3 |
size 83945
|
tqc-PandaReachDense-v2/pytorch_variables.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 747
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cf4c8249cdec34a5beaadc1f368b4122133ab0f1e365206f2a8df73b4860b3f
|
3 |
size 747
|
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 sha256:9fc3e8d3487d239e7b48aae3be4bea0c6068d1b53e651df3e97824e2fdd997d7
|
3 |
+
size 62178
|
vec_normalize.pkl
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 sha256:3125b189002daa079ce537717a13e9c7a4f7e19b39f8eb973e14bb221a5099aa
|
3 |
+
size 5882
|