Test commit

-step-0-to-step-1000.meta.json

@@ -1 +1 @@
-{"step_id": 0, "content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)\\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\\nlibavutil      56. 31.100 / 56. 31.100\\nlibavcodec     58. 54.100 / 58. 54.100\\nlibavformat    58. 29.100 / 58. 29.100\\nlibavdevice    58.  8.100 / 58.  8.100\\nlibavfilter     7. 57.100 /  7. 57.100\\nlibavresample   4.  0.  0 /  4.  0.  0\\nlibswscale      5.  5.100 /  5.  5.100\\nlibswresample   3.  5.100 /  3.  5.100\\nlibpostproc    55.  5.100 / 55.  5.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "600x400", "-pix_fmt", "rgb24", "-r", "50", "-i", "-", "-an", "-r", "50", "-vcodec", "mpeg4", "-pix_fmt", "bgr24", "-r", "50", "/tmp/tmp333hnhjk/-step-0-to-step-1000.mp4"]}}
+{"step_id": 0, "content_type": "video/mp4", "encoder_version": {"backend": "ffmpeg", "version": "b'ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers\\nbuilt with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)\\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\\nlibavutil      56. 31.100 / 56. 31.100\\nlibavcodec     58. 54.100 / 58. 54.100\\nlibavformat    58. 29.100 / 58. 29.100\\nlibavdevice    58.  8.100 / 58.  8.100\\nlibavfilter     7. 57.100 /  7. 57.100\\nlibavresample   4.  0.  0 /  4.  0.  0\\nlibswscale      5.  5.100 /  5.  5.100\\nlibswresample   3.  5.100 /  3.  5.100\\nlibpostproc    55.  5.100 / 55.  5.100\\n'", "cmdline": ["ffmpeg", "-nostats", "-loglevel", "error", "-y", "-f", "rawvideo", "-s:v", "600x400", "-pix_fmt", "rgb24", "-r", "50", "-i", "-", "-an", "-r", "50", "-vcodec", "mpeg4", "-pix_fmt", "bgr24", "-r", "50", "/tmp/tmpv04h5dy_/-step-0-to-step-1000.mp4"]}}

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -542.77 +/- 0.00
+      value: -479.21 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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: 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 ActorCriticPolicy.__init__ at 0x7fd541305430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd5413054c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd541305550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd5413055e0>", "_build": "<function ActorCriticPolicy._build at 0x7fd541305670>", "forward": "<function ActorCriticPolicy.forward at 0x7fd541305700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd541305790>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd541305820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd5413058b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd541305940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd5413059d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fd54136cae0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657184031.7603972, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAayTj6rCLE/FhEbP0SLm75egZ2+KjgJvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVhgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFYvaG9tZS9vc2Fuc2V2aWVyby8ubG9jYWwvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDXVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    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\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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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: 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 ActorCriticPolicy.__init__ at 0x7faa44638430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faa446384c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faa44638550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faa446385e0>", "_build": "<function ActorCriticPolicy._build at 0x7faa44638670>", "forward": "<function ActorCriticPolicy.forward at 0x7faa44638700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faa44638790>", "_predict": "<function ActorCriticPolicy._predict at 0x7faa44638820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faa446388b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faa44638940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faa446389d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7faa4469fae0>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 4, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 2048, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1657184341.2829957, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM16Gbyzxbo/aymDvTlDFj4zpDC8f+W/vQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -203.8, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 10, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVhgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjFYvaG9tZS9vc2Fuc2V2aWVyby8ubG9jYWwvbGliL3B5dGhvbjMuOC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4BDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5RoDXVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "target_kl": null, "system_info": {"OS": "Linux-5.13.0-52-generic-x86_64-with-glibc2.17 #59~20.04.1-Ubuntu SMP Thu Jun 16 21:21:28 UTC 2022", "Python": "3.8.13", "Stable-Baselines3": "1.4.0", "PyTorch": "1.12.0+cu102", "GPU Enabled": "True", "Numpy": "1.23.0", "Gym": "0.19.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2533ac8fc1381cc9a0a1f08570174902b8804d15359013bcb1380fc0d41cfe7b
+oid sha256:8b857e3f8a90fbfdf8050882f7539c8d4da4b599c06a1f5a82fc8e2ad5e6e87d
 size 141488

ppo-LunarLander-v2/data

@@ -4,19 +4,19 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    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\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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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: 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 ActorCriticPolicy.__init__ at 0x7fd541305430>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd5413054c0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd541305550>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd5413055e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fd541305670>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fd541305700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd541305790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fd541305820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd5413058b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd541305940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd5413059d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7faa44638430>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faa446384c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faa44638550>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faa446385e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7faa44638670>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7faa44638700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faa44638790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7faa44638820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faa446388b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faa44638940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faa446389d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7fd54136cae0>"
+        "_abc_impl": "<_abc_data object at 0x7faa4469fae0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -47,7 +47,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1657184031.7603972,
+    "start_time": 1657184341.2829957,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -56,7 +56,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAayTj6rCLE/FhEbP0SLm75egZ2+KjgJvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAM16Gbyzxbo/aymDvTlDFj4zpDC8f+W/vQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -69,7 +69,7 @@
     "_current_progress_remaining": -203.8,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV7QMAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMI9l580R4pZsCUhpRSlIwBbJRLXYwBdJRHP6JgTh5xBE91fZQoaAZoCWgPQwhjtI6qJiJbwJSGlFKUaBVLUGgWRz+vmPo3aSLZdX2UKGgGaAloD0MI0m70MZ+aZ8CUhpRSlGgVS0FoFkc/tP9DQZ4wAXV9lChoBmgJaA9DCJbtQ96yDHbAlIaUUpRoFUtsaBZHP725Yoy9EkV1fZQoaAZoCWgPQwg/qfbpeAJCwJSGlFKUaBVLQWgWRz/BcO9WZJCjdX2UKGgGaAloD0MIZVJDG4C/UcCUhpRSlGgVS0VoFkc/xCtq59Vmz3V9lChoBmgJaA9DCO0OKQZI/lLAlIaUUpRoFUtwaBZHP8jD8+A3DN11fZQoaAZoCWgPQwgp6sw9JH1fwJSGlFKUaBVLZGgWRz/M5S3solUqdX2UKGgGaAloD0MI6Etvfy5nYMCUhpRSlGgVS11oFkc/0EmUnogV5HV9lChoBmgJaA9DCIP7AQ/MSXrAlIaUUpRoFUtcaBZHP9IsRQJokAx1fZQoaAZoCWgPQwhaY9AJoXlSwJSGlFKUaBVLUGgWRz/TyU9pyp71dX2UKGgGaAloD0MIYd14d2SvYsCUhpRSlGgVS19oFkc/1aNIbwSamXV9lChoBmgJaA9DCGcqxCOxmnXAlIaUUpRoFUtbaBZHP9ePmxMWXTp1fZQoaAZoCWgPQwj0wMdgxWx+wJSGlFKUaBVLZGgWRz/ZphnanJkodX2UKGgGaAloD0MIlNqLaPvmcsCUhpRSlGgVS3BoFkc/3BAWznied3V9lChoBmgJaA9DCG2MnfCSsGnAlIaUUpRoFUtiaBZHP94R/ViF0xN1fZQoaAZoCWgPQwjLhjWVhRB7wJSGlFKUaBVLcmgWRz/gL2pQ1rIpdX2UKGgGaAloD0MI1xcJbTmLVcCUhpRSlGgVS0doFkc/4Si7CiyprHV9lChoBmgJaA9DCPVMLzEWQ2LAlIaUUpRoFUtNaBZHP+H3SKFZgXx1fZQoaAZoCWgPQwjCpWPOs8h7wJSGlFKUaBVLgWgWRz/jSTpxFRYSdX2UKGgGaAloD0MI4jsx68UBYcCUhpRSlGgVS1xoFkc/5DErGza9K3V9lChoBmgJaA9DCI6SV+cYDlbAlIaUUpRoFUtOaBZHP+T1pTMqz7d1ZS4="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e5ff989d8f66cafdd3863145d3cde8ab6506ec30455537faef32b854c163dfe
+oid sha256:1f897cb2501acdc86d4994627740b28bbbec5936c94e51afd43bcd76cc9107e4
 size 87545

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63784f049d27a5f808286c8ab88b70a1972c1010a62d586c4a812c0981a5f222
+oid sha256:b324eebfe247bf84e2c1098ef26586af40373e3c94c4f4b11bac43085865a2ed
 size 43073

results.json

@@ -1 +1 @@
-{"mean_reward": -542.770244, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T10:53:55.004454"}
+{"mean_reward": -479.211951, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 1, "eval_datetime": "2022-07-07T10:59:04.585223"}