Hugging Face's logo

n1kolAI
/
a2c-PandaReachDense-v3

Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results
Model card Files Community
n1kolAI commited on
Commit
eabfc6b
•
1 Parent(s): 832682b

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. a2c-PandaReachDense-v3.zip +2 -2
  3. a2c-PandaReachDense-v3/data +29 -32
  4. a2c-PandaReachDense-v3/policy.optimizer.pth +2 -2
  5. a2c-PandaReachDense-v3/policy.pth +2 -2
  6. config.json +1 -1
  7. replay.mp4 +0 -0
  8. results.json +1 -1
  9. vec_normalize.pkl +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
- value: -25.45 +/- 3.75
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: -0.26 +/- 0.10
20
  name: mean_reward
21
  verified: false
22
  ---
a2c-PandaReachDense-v3.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c6e382d3c68b636c0bb774515f9984390105b6e504e523c5463321351ed0594
3
- size 39392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a91ac96033ab21558191bea696ab6ac2a6ba7c4c6f9dad7b0cc3729d289a81
3
+ size 110005
a2c-PandaReachDense-v3/data CHANGED
@@ -4,23 +4,14 @@
4
  ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Uses the CombinedExtractor\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
7
- "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7cae3ce739a0>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x7cae3ce80b00>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
13
  ":type:": "<class 'dict'>",
14
- ":serialized:": "gAWV2wAAAAAAAAB9lCiMCG5ldF9hcmNolH2UKIwCcGmUXZRLQGGMAnZmlF2US0BhdYwNYWN0aXZhdGlvbl9mbpSMG3RvcmNoLm5uLm1vZHVsZXMuYWN0aXZhdGlvbpSMBFRhbmiUk5SMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
15
- "net_arch": {
16
- "pi": [
17
- 64
18
- ],
19
- "vf": [
20
- 64
21
- ]
22
- },
23
- "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
24
  "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
25
  "optimizer_kwargs": {
26
  "alpha": 0.99,
@@ -33,21 +24,27 @@
33
  "_num_timesteps_at_start": 0,
34
  "seed": null,
35
  "action_noise": null,
36
- "start_time": 1710619566855940818,
37
- "learning_rate": 0.00857,
38
  "tensorboard_log": null,
39
  "_last_obs": {
40
  ":type:": "<class 'collections.OrderedDict'>",
41
- ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA+ZtvvY5L3r4kOwQ/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAuR1WPBnr+L1M+1w+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAAD5m2+9jkveviQ7BD9eZkG9tYccvRq6uDyUaA5LAUsGhpRoEnSUUpR1Lg==",
42
- "achieved_goal": "[[-0.05849836 -0.4341702 0.5165274 ]]",
43
- "desired_goal": "[[ 0.01306861 -0.12154216 0.21580237]]",
44
- "observation": "[[-0.05849836 -0.4341702 0.5165274 -0.04721677 -0.03821536 0.02254968]]"
45
  },
46
  "_last_episode_starts": {
47
  ":type:": "<class 'numpy.ndarray'>",
48
- ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
 
 
 
 
 
 
 
49
  },
50
- "_last_original_obs": null,
51
  "_episode_num": 0,
52
  "use_sde": false,
53
  "sde_sample_freq": -1,
@@ -55,16 +52,16 @@
55
  "_stats_window_size": 100,
56
  "ep_info_buffer": {
57
  ":type:": "<class 'collections.deque'>",
58
- ":serialized:": "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"
59
  },
60
  "ep_success_buffer": {
61
  ":type:": "<class 'collections.deque'>",
62
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
63
  },
64
- "_n_updates": 200000,
65
  "n_steps": 5,
66
- "gamma": 0.991229,
67
- "gae_lambda": 0.9467716,
68
  "ent_coef": 0.0,
69
  "vf_coef": 0.5,
70
  "max_grad_norm": 0.5,
@@ -74,13 +71,13 @@
74
  "__module__": "stable_baselines3.common.buffers",
75
  "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
76
  "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\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: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
77
- "__init__": "<function DictRolloutBuffer.__init__ at 0x7cae3cdce320>",
78
- "reset": "<function DictRolloutBuffer.reset at 0x7cae3cdce3b0>",
79
- "add": "<function DictRolloutBuffer.add at 0x7cae3cdce440>",
80
- "get": "<function DictRolloutBuffer.get at 0x7cae3cdce4d0>",
81
- "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7cae3cdce560>",
82
  "__abstractmethods__": "frozenset()",
83
- "_abc_impl": "<_abc._abc_data object at 0x7cae3cdbf180>"
84
  },
85
  "rollout_buffer_kwargs": {},
86
  "normalize_advantage": false,
@@ -107,9 +104,9 @@
107
  "high_repr": "1.0",
108
  "_np_random": null
109
  },
110
- "n_envs": 1,
111
  "lr_schedule": {
112
  ":type:": "<class 'function'>",
113
- ":serialized:": "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"
114
  }
115
  }
 
4
  ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__doc__": "\n MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Uses the CombinedExtractor\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ",
7
+ "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7e6bfb373d90>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7e6bfb375e40>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
13
  ":type:": "<class 'dict'>",
14
+ ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
 
 
 
 
 
 
 
 
 
15
  "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
16
  "optimizer_kwargs": {
17
  "alpha": 0.99,
 
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
+ "start_time": 1710658425510594438,
28
+ "learning_rate": 0.0007,
29
  "tensorboard_log": null,
30
  "_last_obs": {
31
  ":type:": "<class 'collections.OrderedDict'>",
32
+ ":serialized:": "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",
33
+ "achieved_goal": "[[-0.06447008 0.41300145 -0.18099524]\n [ 0.2682196 -0.01676638 0.4053802 ]\n [ 0.2682196 -0.01676638 0.4053802 ]\n [ 1.3410006 -0.6139541 -0.76668096]]",
34
+ "desired_goal": "[[-0.82226527 0.9019127 -1.4054888 ]\n [-0.08094234 0.4900723 1.1933835 ]\n [ 1.0715759 -0.37454018 -1.3559637 ]\n [ 1.5711657 -0.29741922 -1.3860029 ]]",
35
+ "observation": "[[-0.06447008 0.41300145 -0.18099524 -1.7814618 1.6410704 -1.4046705 ]\n [ 0.2682196 -0.01676638 0.4053802 0.42948332 -0.00427954 0.36737928]\n [ 0.2682196 -0.01676638 0.4053802 0.42948332 -0.00427954 0.36737928]\n [ 1.3410006 -0.6139541 -0.76668096 0.17523886 -0.16876578 -1.6162992 ]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
40
+ },
41
+ "_last_original_obs": {
42
+ ":type:": "<class 'collections.OrderedDict'>",
43
+ ":serialized:": "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",
44
+ "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]",
45
+ "desired_goal": "[[-0.05084587 -0.12666795 0.13788705]\n [ 0.0980643 0.01315741 0.14952038]\n [ 0.13057372 -0.1301065 0.13246903]\n [-0.06354705 -0.02022269 0.19933303]]",
46
+ "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"
47
  },
 
48
  "_episode_num": 0,
49
  "use_sde": false,
50
  "sde_sample_freq": -1,
 
52
  "_stats_window_size": 100,
53
  "ep_info_buffer": {
54
  ":type:": "<class 'collections.deque'>",
55
+ ":serialized:": "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"
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
59
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
60
  },
61
+ "_n_updates": 50000,
62
  "n_steps": 5,
63
+ "gamma": 0.99,
64
+ "gae_lambda": 1.0,
65
  "ent_coef": 0.0,
66
  "vf_coef": 0.5,
67
  "max_grad_norm": 0.5,
 
71
  "__module__": "stable_baselines3.common.buffers",
72
  "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
73
  "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\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: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
74
+ "__init__": "<function DictRolloutBuffer.__init__ at 0x7e6bfb2ca710>",
75
+ "reset": "<function DictRolloutBuffer.reset at 0x7e6bfb2ca7a0>",
76
+ "add": "<function DictRolloutBuffer.add at 0x7e6bfb2ca830>",
77
+ "get": "<function DictRolloutBuffer.get at 0x7e6bfb2ca8c0>",
78
+ "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7e6bfb2ca950>",
79
  "__abstractmethods__": "frozenset()",
80
+ "_abc_impl": "<_abc._abc_data object at 0x7e6bfb2dc5c0>"
81
  },
82
  "rollout_buffer_kwargs": {},
83
  "normalize_advantage": false,
 
104
  "high_repr": "1.0",
105
  "_np_random": null
106
  },
107
+ "n_envs": 4,
108
  "lr_schedule": {
109
  ":type:": "<class 'function'>",
110
+ ":serialized:": "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"
111
  }
112
  }
a2c-PandaReachDense-v3/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1910f85ed6ab15c85186caa5cb68354439e71edc56e9c0fbd219bfc8a96d095f
3
- size 10812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80754ee731b36134191c344858b6eecbecaf672ccea22d8e0f2c7497b9894589
3
+ size 45039
a2c-PandaReachDense-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d7b6d493d040357db77e2089aad31d72514d046fb072960b61f589cca1a4504
3
- size 11772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1973b59d3c3099fa5437b9f09f3f73e1dc80a0678c65fe8fa92de2623b9ac02c
3
+ size 46319
config.json CHANGED
@@ -1 +1 @@
1
- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Uses the CombinedExtractor\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7cae3ce739a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cae3ce80b00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWV2wAAAAAAAAB9lCiMCG5ldF9hcmNolH2UKIwCcGmUXZRLQGGMAnZmlF2US0BhdYwNYWN0aXZhdGlvbl9mbpSMG3RvcmNoLm5uLm1vZHVsZXMuYWN0aXZhdGlvbpSMBFRhbmiUk5SMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "net_arch": {"pi": [64], "vf": [64]}, "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710619566855940818, "learning_rate": 0.00857, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA+ZtvvY5L3r4kOwQ/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAuR1WPBnr+L1M+1w+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAAD5m2+9jkveviQ7BD9eZkG9tYccvRq6uDyUaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[-0.05849836 -0.4341702 0.5165274 ]]", "desired_goal": "[[ 0.01306861 -0.12154216 0.21580237]]", "observation": "[[-0.05849836 -0.4341702 0.5165274 -0.04721677 -0.03821536 0.02254968]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 200000, "n_steps": 5, "gamma": 0.991229, "gae_lambda": 0.9467716, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\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: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7cae3cdce320>", "reset": "<function DictRolloutBuffer.reset at 0x7cae3cdce3b0>", "add": "<function DictRolloutBuffer.add at 0x7cae3cdce440>", "get": "<function DictRolloutBuffer.get at 0x7cae3cdce4d0>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7cae3cdce560>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cae3cdbf180>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "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": null}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
 
1
+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n MultiInputActorClass policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space (Tuple)\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param use_expln: Use ``expln()`` function instead of ``exp()`` 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 squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Uses the CombinedExtractor\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ", "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7e6bfb373d90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e6bfb375e40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710658425510594438, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.06447008 0.41300145 -0.18099524]\n [ 0.2682196 -0.01676638 0.4053802 ]\n [ 0.2682196 -0.01676638 0.4053802 ]\n [ 1.3410006 -0.6139541 -0.76668096]]", "desired_goal": "[[-0.82226527 0.9019127 -1.4054888 ]\n [-0.08094234 0.4900723 1.1933835 ]\n [ 1.0715759 -0.37454018 -1.3559637 ]\n [ 1.5711657 -0.29741922 -1.3860029 ]]", "observation": "[[-0.06447008 0.41300145 -0.18099524 -1.7814618 1.6410704 -1.4046705 ]\n [ 0.2682196 -0.01676638 0.4053802 0.42948332 -0.00427954 0.36737928]\n [ 0.2682196 -0.01676638 0.4053802 0.42948332 -0.00427954 0.36737928]\n [ 1.3410006 -0.6139541 -0.76668096 0.17523886 -0.16876578 -1.6162992 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01]]", "desired_goal": "[[-0.05084587 -0.12666795 0.13788705]\n [ 0.0980643 0.01315741 0.14952038]\n [ 0.13057372 -0.1301065 0.13246903]\n [-0.06354705 -0.02022269 0.19933303]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\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: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7e6bfb2ca710>", "reset": "<function DictRolloutBuffer.reset at 0x7e6bfb2ca7a0>", "add": "<function DictRolloutBuffer.add at 0x7e6bfb2ca830>", "get": "<function DictRolloutBuffer.get at 0x7e6bfb2ca8c0>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7e6bfb2ca950>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e6bfb2dc5c0>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "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": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.2.1+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -25.44760881587863, "std_reward": 3.746749864146985, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-16T21:32:35.394981"}
 
1
+ {"mean_reward": -0.2599623199552298, "std_reward": 0.10272780033969578, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T07:47:40.987386"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6362e1f6e61ebba8da7ce5829ac7b80c3ff6c2a29a3f3970e41d554c2ca19c37
3
  size 2646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8cd6fad5d9976a09126b3ac8e3ef18713395336a83739ab60f5d27d45cea22
3
  size 2646