Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+library_name: stable-baselines3
+tags:
+- FrozenLake-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: FrozenLake-v1
+      type: FrozenLake-v1
+    metrics:
+    - type: mean_reward
+      value: 0.50 +/- 0.50
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **FrozenLake-v1**
+This is a trained model of a **DQN** agent playing **FrozenLake-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo dqn --env FrozenLake-v1 -orga Sushmitha047 -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env FrozenLake-v1  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo dqn --env FrozenLake-v1 -orga Sushmitha047 -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env FrozenLake-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env FrozenLake-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env FrozenLake-v1 -f logs/ -orga Sushmitha047
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 32),
+             ('buffer_size', 100000),
+             ('exploration_final_eps', 0.01),
+             ('exploration_fraction', 0.1),
+             ('gradient_steps', 1),
+             ('learning_rate', 0.0001),
+             ('learning_starts', 1000),
+             ('n_timesteps', 100000.0),
+             ('optimize_memory_usage', False),
+             ('policy', 'MlpPolicy'),
+             ('target_update_interval', 1000),
+             ('train_freq', 4),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - fl_dqn.yml
+  - - device
+    - auto
+  - - env
+    - FrozenLake-v1
+  - - env_kwargs
+    - null
+  - - eval_env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - fl_logs/
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1119584521
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 32
+  - - buffer_size
+    - 100000
+  - - exploration_final_eps
+    - 0.01
+  - - exploration_fraction
+    - 0.1
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - 0.0001
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 100000.0
+  - - optimize_memory_usage
+    - false
+  - - policy
+    - MlpPolicy
+  - - target_update_interval
+    - 1000
+  - - train_freq
+    - 4

dqn-FrozenLake-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dda49986e7db29dfd47af322401a3ffb2703bf6f6a0ebbeb84259f6b3af70fb
+size 115453

dqn-FrozenLake-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.4.0a7

dqn-FrozenLake-v1/data

@@ -0,0 +1,117 @@
+{
+    "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 0x7bbf83503910>",
+        "_build": "<function DQNPolicy._build at 0x7bbf835039a0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7bbf83503a30>",
+        "forward": "<function DQNPolicy.forward at 0x7bbf83503ac0>",
+        "_predict": "<function DQNPolicy._predict at 0x7bbf83503b50>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7bbf83503be0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7bbf83503c70>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7bbf83520080>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1727969592213156689,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
+    },
+    "_episode_num": 3350,
+    "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": 24750,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIEAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "16",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1,
+    "batch_size": 32,
+    "learning_starts": 1000,
+    "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",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__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 0x7bbf83649120>",
+        "add": "<function ReplayBuffer.add at 0x7bbf836491b0>",
+        "sample": "<function ReplayBuffer.sample at 0x7bbf83649240>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7bbf836492d0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7bbf83649360>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7bbf837c8f00>"
+    },
+    "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": 0.01,
+    "exploration_fraction": 0.1,
+    "target_update_interval": 1000,
+    "_n_calls": 100000,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.01,
+    "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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"
+    }
+}

dqn-FrozenLake-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b9ceeac16744e3a2320fd7d97c5062ac45cd65772792e3c28885bb592e9405
+size 49504

dqn-FrozenLake-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be93c62ff1d17e173d7e8d86b2d71b39c31ec7a522fb045bf41b991b68b1d13
+size 48562

dqn-FrozenLake-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

dqn-FrozenLake-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.4.0a7
+- PyTorch: 2.4.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

results.json

@@ -0,0 +1 @@
+{"mean_reward": 0.5, "std_reward": 0.5, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-03T15:38:26.757039"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628ea2aefac95c6bce6a86d0defec7f3f82e5fb8c29b3f73e7a6977fbcf2643c
+size 60832