AlifsyahNst
commited on
Commit
•
4acd3c6
1
Parent(s):
22cc5cd
Upload DQNCartPole-v1 trained agent
Browse files- README.md +1 -1
- config.json +1 -1
- dqn-CartPole-v1.zip +2 -2
- dqn-CartPole-v1/data +14 -14
- dqn-CartPole-v1/policy.optimizer.pth +1 -1
- dqn-CartPole-v1/policy.pth +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: CartPole-v1
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: CartPole-v1
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 9.50 +/- 0.67
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n Policy class with Q-Value Net and target net for DQN\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 ", "__init__": "<function DQNPolicy.__init__ at 0x7bdabe69bb50>", "_build": "<function DQNPolicy._build at 0x7bdabe69bbe0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7bdabe69bc70>", "forward": "<function DQNPolicy.forward at 0x7bdabe69bd00>", "_predict": "<function DQNPolicy._predict at 0x7bdabe69bd90>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7bdabe69be20>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7bdabe69beb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bdabe6ab180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718257700880016928, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 9962, "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": 15547, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "buffer_size": 100000, "batch_size": 32, "learning_starts": 5000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__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: PyTorch 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 Cannot be used in combination with handle_timeout_termination.\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 ", "__init__": "<function ReplayBuffer.__init__ at 0x7bdabe698040>", "add": "<function ReplayBuffer.add at 0x7bdabe6980d0>", "sample": "<function ReplayBuffer.sample at 0x7bdabe698160>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7bdabe6981f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bdabe694cc0>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.05, "exploration_fraction": 0.3, "target_update_interval": 625, "_n_calls": 62500, "max_grad_norm": 10, "exploration_rate": 0.05, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9QYk3S8an8hZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n Policy class with Q-Value Net and target net for DQN\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 ", "__init__": "<function DQNPolicy.__init__ at 0x7bdabe69bb50>", "_build": "<function DQNPolicy._build at 0x7bdabe69bbe0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7bdabe69bc70>", "forward": "<function DQNPolicy.forward at 0x7bdabe69bd00>", "_predict": "<function DQNPolicy._predict at 0x7bdabe69bd90>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7bdabe69be20>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7bdabe69beb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bdabe6ab180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 700032, "_total_timesteps": 700000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718258252732516730, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 65398, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -4.571428571420455e-05, "_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": 10860, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "buffer_size": 100000, "batch_size": 64, "learning_starts": 5000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__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: PyTorch 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 Cannot be used in combination with handle_timeout_termination.\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 ", "__init__": "<function ReplayBuffer.__init__ at 0x7bdabe698040>", "add": "<function ReplayBuffer.add at 0x7bdabe6980d0>", "sample": "<function ReplayBuffer.sample at 0x7bdabe698160>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7bdabe6981f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7bdabe694cc0>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.05, "exploration_fraction": 0.3, "target_update_interval": 625, "_n_calls": 43752, "max_grad_norm": 10, "exploration_rate": 0.05, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
dqn-CartPole-v1.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:d9d907d380cef3584760d179ead41ebd90f15566a6bf5c547e0c13f1d2d19bf4
|
3 |
+
size 100784
|
dqn-CartPole-v1/data
CHANGED
@@ -17,17 +17,17 @@
|
|
17 |
},
|
18 |
"verbose": 1,
|
19 |
"policy_kwargs": {},
|
20 |
-
"num_timesteps":
|
21 |
-
"_total_timesteps":
|
22 |
"_num_timesteps_at_start": 0,
|
23 |
"seed": null,
|
24 |
"action_noise": null,
|
25 |
-
"start_time":
|
26 |
-
"learning_rate": 0.
|
27 |
"tensorboard_log": null,
|
28 |
"_last_obs": {
|
29 |
":type:": "<class 'numpy.ndarray'>",
|
30 |
-
":serialized:": "
|
31 |
},
|
32 |
"_last_episode_starts": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
@@ -35,22 +35,22 @@
|
|
35 |
},
|
36 |
"_last_original_obs": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
-
":serialized:": "
|
39 |
},
|
40 |
-
"_episode_num":
|
41 |
"use_sde": false,
|
42 |
"sde_sample_freq": -1,
|
43 |
-
"_current_progress_remaining":
|
44 |
"_stats_window_size": 100,
|
45 |
"ep_info_buffer": {
|
46 |
":type:": "<class 'collections.deque'>",
|
47 |
-
":serialized:": "
|
48 |
},
|
49 |
"ep_success_buffer": {
|
50 |
":type:": "<class 'collections.deque'>",
|
51 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
52 |
},
|
53 |
-
"_n_updates":
|
54 |
"observation_space": {
|
55 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
56 |
":serialized:": "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",
|
@@ -68,7 +68,7 @@
|
|
68 |
},
|
69 |
"action_space": {
|
70 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
71 |
-
":serialized:": "gAWVpQEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////
|
72 |
"n": "2",
|
73 |
"start": "0",
|
74 |
"_shape": [],
|
@@ -77,7 +77,7 @@
|
|
77 |
},
|
78 |
"n_envs": 16,
|
79 |
"buffer_size": 100000,
|
80 |
-
"batch_size":
|
81 |
"learning_starts": 5000,
|
82 |
"tau": 1.0,
|
83 |
"gamma": 0.99,
|
@@ -105,12 +105,12 @@
|
|
105 |
"exploration_final_eps": 0.05,
|
106 |
"exploration_fraction": 0.3,
|
107 |
"target_update_interval": 625,
|
108 |
-
"_n_calls":
|
109 |
"max_grad_norm": 10,
|
110 |
"exploration_rate": 0.05,
|
111 |
"lr_schedule": {
|
112 |
":type:": "<class 'function'>",
|
113 |
-
":serialized:": "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
|
114 |
},
|
115 |
"batch_norm_stats": [],
|
116 |
"batch_norm_stats_target": [],
|
|
|
17 |
},
|
18 |
"verbose": 1,
|
19 |
"policy_kwargs": {},
|
20 |
+
"num_timesteps": 700032,
|
21 |
+
"_total_timesteps": 700000,
|
22 |
"_num_timesteps_at_start": 0,
|
23 |
"seed": null,
|
24 |
"action_noise": null,
|
25 |
+
"start_time": 1718258252732516730,
|
26 |
+
"learning_rate": 0.0001,
|
27 |
"tensorboard_log": null,
|
28 |
"_last_obs": {
|
29 |
":type:": "<class 'numpy.ndarray'>",
|
30 |
+
":serialized:": "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"
|
31 |
},
|
32 |
"_last_episode_starts": {
|
33 |
":type:": "<class 'numpy.ndarray'>",
|
|
|
35 |
},
|
36 |
"_last_original_obs": {
|
37 |
":type:": "<class 'numpy.ndarray'>",
|
38 |
+
":serialized:": "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"
|
39 |
},
|
40 |
+
"_episode_num": 65398,
|
41 |
"use_sde": false,
|
42 |
"sde_sample_freq": -1,
|
43 |
+
"_current_progress_remaining": -4.571428571420455e-05,
|
44 |
"_stats_window_size": 100,
|
45 |
"ep_info_buffer": {
|
46 |
":type:": "<class 'collections.deque'>",
|
47 |
+
":serialized:": "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"
|
48 |
},
|
49 |
"ep_success_buffer": {
|
50 |
":type:": "<class 'collections.deque'>",
|
51 |
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
52 |
},
|
53 |
+
"_n_updates": 10860,
|
54 |
"observation_space": {
|
55 |
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
56 |
":serialized:": "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",
|
|
|
68 |
},
|
69 |
"action_space": {
|
70 |
":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
|
71 |
+
":serialized:": "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",
|
72 |
"n": "2",
|
73 |
"start": "0",
|
74 |
"_shape": [],
|
|
|
77 |
},
|
78 |
"n_envs": 16,
|
79 |
"buffer_size": 100000,
|
80 |
+
"batch_size": 64,
|
81 |
"learning_starts": 5000,
|
82 |
"tau": 1.0,
|
83 |
"gamma": 0.99,
|
|
|
105 |
"exploration_final_eps": 0.05,
|
106 |
"exploration_fraction": 0.3,
|
107 |
"target_update_interval": 625,
|
108 |
+
"_n_calls": 43752,
|
109 |
"max_grad_norm": 10,
|
110 |
"exploration_rate": 0.05,
|
111 |
"lr_schedule": {
|
112 |
":type:": "<class 'function'>",
|
113 |
+
":serialized:": "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"
|
114 |
},
|
115 |
"batch_norm_stats": [],
|
116 |
"batch_norm_stats_target": [],
|
dqn-CartPole-v1/policy.optimizer.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42272
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe2434685f8d92578b5ffd08ce95b88c40ce499a5d5072ffc3439d709c18a84
|
3 |
size 42272
|
dqn-CartPole-v1/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41394
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6db1b07edf81e61652b5f2611d85f688d25af66ec3bf400e205699174821cbe
|
3 |
size 41394
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 9.5, "std_reward": 0.6708203932499369, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-13T06:07:55.086747"}
|