Initial commit
Browse files- DDPG-PandaReach-v3.zip +3 -0
- DDPG-PandaReach-v3/_stable_baselines3_version +1 -0
- DDPG-PandaReach-v3/actor.optimizer.pth +3 -0
- DDPG-PandaReach-v3/critic.optimizer.pth +3 -0
- DDPG-PandaReach-v3/data +120 -0
- DDPG-PandaReach-v3/policy.pth +3 -0
- DDPG-PandaReach-v3/pytorch_variables.pth +3 -0
- DDPG-PandaReach-v3/system_info.txt +9 -0
- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- vec_normalize.pkl +3 -0
DDPG-PandaReach-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdb9b4fca65f9adf4d40f6b29ddc38a3a8c368f91c7ae0b9d331b6b4ef1f2125
|
3 |
+
size 4091733
|
DDPG-PandaReach-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.2.1
|
DDPG-PandaReach-v3/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:504e834fa1edeb78ad6ce4bd04284947690c11601c8297e87c61cb40c2c0df7a
|
3 |
+
size 1016544
|
DDPG-PandaReach-v3/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d328fd90b3d1bc5276fe3bcf751a94792dde3d76a17dd0327de1ee6286474f
|
3 |
+
size 1021280
|
DDPG-PandaReach-v3/data
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
|
5 |
+
"__module__": "stable_baselines3.td3.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\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 features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features 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_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 0x784654cb9b40>",
|
8 |
+
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc._abc_data object at 0x784654cbcc40>"
|
10 |
+
},
|
11 |
+
"verbose": 1,
|
12 |
+
"policy_kwargs": {
|
13 |
+
"n_critics": 1
|
14 |
+
},
|
15 |
+
"num_timesteps": 30011,
|
16 |
+
"_total_timesteps": 30000,
|
17 |
+
"_num_timesteps_at_start": 0,
|
18 |
+
"seed": null,
|
19 |
+
"action_noise": null,
|
20 |
+
"start_time": 1700567699907138358,
|
21 |
+
"learning_rate": 0.001,
|
22 |
+
"tensorboard_log": null,
|
23 |
+
"_last_obs": null,
|
24 |
+
"_last_episode_starts": {
|
25 |
+
":type:": "<class 'numpy.ndarray'>",
|
26 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
27 |
+
},
|
28 |
+
"_last_original_obs": {
|
29 |
+
":type:": "<class 'collections.OrderedDict'>",
|
30 |
+
":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAADdoQvoVdTb2Mvw4+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==",
|
31 |
+
"achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
|
32 |
+
"desired_goal": "[[-0.1414568 -0.05013802 0.13940257]]",
|
33 |
+
"observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
|
34 |
+
},
|
35 |
+
"_episode_num": 7512,
|
36 |
+
"use_sde": false,
|
37 |
+
"sde_sample_freq": -1,
|
38 |
+
"_current_progress_remaining": -0.0003666666666666263,
|
39 |
+
"_stats_window_size": 100,
|
40 |
+
"ep_info_buffer": {
|
41 |
+
":type:": "<class 'collections.deque'>",
|
42 |
+
":serialized:": "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"
|
43 |
+
},
|
44 |
+
"ep_success_buffer": {
|
45 |
+
":type:": "<class 'collections.deque'>",
|
46 |
+
":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiJiIiIiYiIiIiJiIiIiImJiIiJiIiIiIiIiYiJiYiIiYiIiYmJiYmJiImIiYmJiImIiImIiYiIiYmJiYmJiImIiYmIiYiJiYmIiYmJiYmJiYiJiYmJiImJiYmJiYmJiYmJiYllLg=="
|
47 |
+
},
|
48 |
+
"_n_updates": 29911,
|
49 |
+
"observation_space": {
|
50 |
+
":type:": "<class 'gymnasium.spaces.dict.Dict'>",
|
51 |
+
":serialized:": "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",
|
52 |
+
"spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])",
|
53 |
+
"_shape": null,
|
54 |
+
"dtype": null,
|
55 |
+
"_np_random": null
|
56 |
+
},
|
57 |
+
"action_space": {
|
58 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
59 |
+
":serialized:": "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",
|
60 |
+
"dtype": "float32",
|
61 |
+
"bounded_below": "[ True True True]",
|
62 |
+
"bounded_above": "[ True True True]",
|
63 |
+
"_shape": [
|
64 |
+
3
|
65 |
+
],
|
66 |
+
"low": "[-1. -1. -1.]",
|
67 |
+
"high": "[1. 1. 1.]",
|
68 |
+
"low_repr": "-1.0",
|
69 |
+
"high_repr": "1.0",
|
70 |
+
"_np_random": "Generator(PCG64)"
|
71 |
+
},
|
72 |
+
"n_envs": 1,
|
73 |
+
"buffer_size": 1000000,
|
74 |
+
"batch_size": 100,
|
75 |
+
"learning_starts": 100,
|
76 |
+
"tau": 0.005,
|
77 |
+
"gamma": 0.99,
|
78 |
+
"gradient_steps": -1,
|
79 |
+
"optimize_memory_usage": false,
|
80 |
+
"replay_buffer_class": {
|
81 |
+
":type:": "<class 'abc.ABCMeta'>",
|
82 |
+
":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=",
|
83 |
+
"__module__": "stable_baselines3.her.her_replay_buffer",
|
84 |
+
"__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}",
|
85 |
+
"__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n .. note::\n\n Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n the current transition can be used when re-sampling.\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 env: The training environment\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\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 :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param copy_info_dict: Whether to copy the info dictionary and pass it to\n ``compute_reward()`` method.\n Please note that the copy may cause a slowdown.\n False by default.\n ",
|
86 |
+
"__init__": "<function HerReplayBuffer.__init__ at 0x784654cba7a0>",
|
87 |
+
"__getstate__": "<function HerReplayBuffer.__getstate__ at 0x784654cba830>",
|
88 |
+
"__setstate__": "<function HerReplayBuffer.__setstate__ at 0x784654cba8c0>",
|
89 |
+
"set_env": "<function HerReplayBuffer.set_env at 0x784654cba950>",
|
90 |
+
"add": "<function HerReplayBuffer.add at 0x784654cba9e0>",
|
91 |
+
"_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x784654cbaa70>",
|
92 |
+
"sample": "<function HerReplayBuffer.sample at 0x784654cbab00>",
|
93 |
+
"_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x784654cbab90>",
|
94 |
+
"_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x784654cbac20>",
|
95 |
+
"_sample_goals": "<function HerReplayBuffer._sample_goals at 0x784654cbacb0>",
|
96 |
+
"truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x784654cbad40>",
|
97 |
+
"__abstractmethods__": "frozenset()",
|
98 |
+
"_abc_impl": "<_abc._abc_data object at 0x784654cbfe40>"
|
99 |
+
},
|
100 |
+
"replay_buffer_kwargs": {
|
101 |
+
"n_sampled_goal": 4,
|
102 |
+
"goal_selection_strategy": "future"
|
103 |
+
},
|
104 |
+
"train_freq": {
|
105 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
106 |
+
":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"
|
107 |
+
},
|
108 |
+
"use_sde_at_warmup": false,
|
109 |
+
"policy_delay": 1,
|
110 |
+
"target_noise_clip": 0.0,
|
111 |
+
"target_policy_noise": 0.1,
|
112 |
+
"lr_schedule": {
|
113 |
+
":type:": "<class 'function'>",
|
114 |
+
":serialized:": "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"
|
115 |
+
},
|
116 |
+
"actor_batch_norm_stats": [],
|
117 |
+
"critic_batch_norm_stats": [],
|
118 |
+
"actor_batch_norm_stats_target": [],
|
119 |
+
"critic_batch_norm_stats_target": []
|
120 |
+
}
|
DDPG-PandaReach-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d58aa081a2e97cd5dfa0715dbd43bc4e7a00a5fb1130a98943b0fb5c63f3bb9
|
3 |
+
size 2036558
|
DDPG-PandaReach-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
DDPG-PandaReach-v3/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.2.1
|
4 |
+
- PyTorch: 2.1.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.23.5
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.29.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- PandaReach-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: DDPG
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: PandaReach-v3
|
16 |
+
type: PandaReach-v3
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: -45.00 +/- 15.00
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **DDPG** Agent playing **PandaReach-v3**
|
25 |
+
This is a trained model of a **DDPG** agent playing **PandaReach-v3**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.td3.policies", "__doc__": "\n Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\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 features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features 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_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 ", "__init__": "<function MultiInputPolicy.__init__ at 0x784654cb9b40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x784654cbcc40>"}, "verbose": 1, "policy_kwargs": {"n_critics": 1}, "num_timesteps": 30011, "_total_timesteps": 30000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700567699907138358, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAADdoQvoVdTb2Mvw4+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[-0.1414568 -0.05013802 0.13940257]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 7512, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0003666666666666263, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiJiIiIiYiIiIiJiIiIiImJiIiJiIiIiIiIiYiJiYiIiYiIiYmJiYmJiImIiYmJiImIiImIiYiIiYmJiYmJiImIiYmIiYiJiYmIiYmJiYmJiYiJiYmJiImJiYmJiYmJiYmJiYllLg=="}, "_n_updates": 29911, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 100, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": -1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVPwAAAAAAAACMJ3N0YWJsZV9iYXNlbGluZXMzLmhlci5oZXJfcmVwbGF5X2J1ZmZlcpSMD0hlclJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.her.her_replay_buffer", "__annotations__": "{'env': typing.Optional[stable_baselines3.common.vec_env.base_vec_env.VecEnv]}", "__doc__": "\n Hindsight Experience Replay (HER) buffer.\n Paper: https://arxiv.org/abs/1707.01495\n\n Replay buffer for sampling HER (Hindsight Experience Replay) transitions.\n\n .. note::\n\n Compared to other implementations, the ``future`` goal sampling strategy is inclusive:\n the current transition can be used when re-sampling.\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 env: The training environment\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\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 :param n_sampled_goal: Number of virtual transitions to create per real transition,\n by sampling new goals.\n :param goal_selection_strategy: Strategy for sampling goals for replay.\n One of ['episode', 'final', 'future']\n :param copy_info_dict: Whether to copy the info dictionary and pass it to\n ``compute_reward()`` method.\n Please note that the copy may cause a slowdown.\n False by default.\n ", "__init__": "<function HerReplayBuffer.__init__ at 0x784654cba7a0>", "__getstate__": "<function HerReplayBuffer.__getstate__ at 0x784654cba830>", "__setstate__": "<function HerReplayBuffer.__setstate__ at 0x784654cba8c0>", "set_env": "<function HerReplayBuffer.set_env at 0x784654cba950>", "add": "<function HerReplayBuffer.add at 0x784654cba9e0>", "_compute_episode_length": "<function HerReplayBuffer._compute_episode_length at 0x784654cbaa70>", "sample": "<function HerReplayBuffer.sample at 0x784654cbab00>", "_get_real_samples": "<function HerReplayBuffer._get_real_samples at 0x784654cbab90>", "_get_virtual_samples": "<function HerReplayBuffer._get_virtual_samples at 0x784654cbac20>", "_sample_goals": "<function HerReplayBuffer._sample_goals at 0x784654cbacb0>", "truncate_last_trajectory": "<function HerReplayBuffer.truncate_last_trajectory at 0x784654cbad40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x784654cbfe40>"}, "replay_buffer_kwargs": {"n_sampled_goal": 4, "goal_selection_strategy": "future"}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVZAAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMB2VwaXNvZGWUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "policy_delay": 1, "target_noise_clip": 0.0, "target_policy_noise": 0.1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "actor_batch_norm_stats": [], "critic_batch_norm_stats": [], "actor_batch_norm_stats_target": [], "critic_batch_norm_stats_target": [], "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (738 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-21T12:03:33.061845"}
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17069d2d17900258df1b104181d83fc27720640c99a026007ee6e4a3b6b19338
|
3 |
+
size 2803
|