Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaPickAndPlace-v3
     metrics:
     - type: mean_reward
-      value: -45.00 +/- 15.00
+      value: -48.27 +/- 9.00
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "sb3_contrib.tqc.policies", "__doc__": "\n    Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_quantiles: Number of quantiles for the critic.\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function MultiInputPolicy.__init__ at 0x7ffa471a2de0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffa46fb2f40>"}, "verbose": 1, "policy_kwargs": {"use_sde": false}, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1760750075408543266, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.45666164  0.7468795   0.13633364]\n [ 1.2482401  -0.6034163   0.10520676]\n [-0.41451776  0.70816296  0.13633144]\n [ 0.219276   -0.28775188  0.13634379]]", "desired_goal": "[[-1.7296052  -1.6431981  -0.8150811 ]\n [-0.91172874 -0.47376338 -0.7072949 ]\n [ 0.67768896  0.14283045  1.4594789 ]\n [-1.7110527   0.79149896 -0.477671  ]]", "observation": "[[ 7.29185402e-01  9.97959197e-01 -3.38843353e-02 -2.00835988e-01\n   1.54472518e+00 -2.66674209e+00 -1.05770171e+00  4.56661642e-01\n   7.46879518e-01  1.36333644e-01 -3.57736135e-03  3.18802940e-03\n  -9.85643361e-03  5.48287891e-02  4.12563095e-03  6.32412657e-02\n  -2.75559979e-03 -1.37450555e-02 -1.23619894e-03]\n [ 1.13952637e+00  5.62435329e-01 -3.58537883e-01  2.36037278e+00\n  -7.13179052e-01  4.69735771e-01  9.53502119e-01  1.24824011e+00\n  -6.03416324e-01  1.05206758e-01  9.28858742e-02 -4.68555123e-01\n   3.61620098e-01  8.16140652e+00 -5.53006983e+00  7.19821095e-01\n  -1.86530030e+00  3.51959014e+00 -2.92868048e-01]\n [ 7.55450487e-01  8.27823877e-01 -8.47191587e-02 -1.17728436e+00\n   1.76338172e+00 -2.22938991e+00 -9.37435687e-01 -4.14517760e-01\n   7.08162963e-01  1.36331439e-01 -3.45642050e-03  3.35177802e-03\n  -9.85575747e-03  5.45598976e-02  4.33983700e-03  6.33124262e-02\n  -4.00712574e-03 -1.51818888e-02 -1.22861471e-03]\n [ 6.46964192e-01  6.38084337e-02 -4.51891482e-01 -6.95268929e-01\n  -1.97337341e+00  2.59410050e-02  8.59932363e-01  2.19275996e-01\n  -2.87751883e-01  1.36343792e-01 -3.57513549e-03  3.34800081e-03\n   1.10912776e+00  5.45607135e-02  4.08879062e-03  6.30674660e-02\n  -2.56768614e-03 -1.51774874e-02 -1.22860912e-03]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.04540964  0.09857238  0.01998945]\n [ 0.13585801 -0.07886199  0.01838389]\n [-0.0541342   0.09348487  0.01998934]\n [ 0.01828517 -0.0373824   0.01998997]]", "desired_goal": "[[-0.14761657 -0.14368674  0.0367117 ]\n [-0.07740058 -0.03983729  0.04381718]\n [ 0.05905344  0.01491816  0.18665504]\n [-0.1460238   0.07252194  0.05895443]]", "observation": "[[ 7.75068300e-03  1.00793801e-01  8.64082575e-02 -2.22494066e-01\n   5.86150467e-01 -1.22808981e+00  5.44464728e-03  4.54096422e-02\n   9.85723808e-02  1.99894495e-02  9.27750392e-08 -2.78913903e-05\n  -1.12769812e-05  2.56027215e-05  4.93884045e-06  2.08185666e-05\n  -2.24239382e-04  1.27332902e-03 -1.32319146e-05]\n [ 1.11389987e-01 -3.80641930e-02  3.75008211e-02  8.29971611e-01\n  -4.20223355e-01  1.67505682e-01  7.46387392e-02  1.35858014e-01\n  -7.88619891e-02  1.83838885e-02  2.63987854e-02 -8.03775415e-02\n   2.14769155e-01  7.71854997e-01 -6.18014753e-01  7.42464811e-02\n  -1.81408465e+00  3.13239479e+00 -5.08441925e-01]\n [ 1.43844215e-02  4.65495996e-02  7.87502453e-02 -6.23741508e-01\n   6.83608234e-01 -1.03348720e+00  9.58231650e-03 -5.41342013e-02\n   9.34848711e-02  1.99893359e-02  3.31901865e-05 -9.05362785e-10\n  -1.08860195e-05  1.44836987e-09  2.88598549e-05  2.88628453e-05\n  -1.44305220e-03  5.61475240e-08 -9.64327729e-09]\n [-1.30158374e-02 -1.97041303e-01  2.34375689e-02 -4.25669104e-01\n  -9.81906414e-01 -2.99635772e-02  7.14195371e-02  1.82851721e-02\n  -3.73823978e-02  1.99899729e-02  7.01928968e-07 -6.44282920e-07\n   6.46963418e-01  7.91315102e-08  8.24747872e-07  1.17060495e-06\n  -4.12374357e-05  3.95657844e-06 -2.70655911e-11]]"}, "_episode_num": 2080, "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiImJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="}, "_n_updates": 24975, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': dict[str, tuple[int, ...]], 'observations': dict[str, numpy.ndarray], 'next_observations': dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function DictReplayBuffer.__init__ at 0x7ffa475cc900>", "add": "<function DictReplayBuffer.add at 0x7ffa475cca40>", "sample": "<function DictReplayBuffer.sample at 0x7ffa475ccae0>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7ffa475ccb80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffa47579e80>"}, "replay_buffer_kwargs": {}, "n_steps": 1, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -4.0, "ent_coef": "auto", "target_update_interval": 1, "top_quantiles_to_drop_per_net": 2, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "{'achieved_goal': Box(-10.0, 10.0, (3,), float32), 'desired_goal': Box(-10.0, 10.0, (3,), float32), 'observation': Box(-10.0, 10.0, (19,), float32)}", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "bounded_below": "[ True  True  True  True]", "high": "[1. 1. 1. 1.]", "bounded_above": "[ True  True  True  True]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 4, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "1.2.1", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "sb3_contrib.tqc.policies", "__doc__": "\n    Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_quantiles: Number of quantiles for the critic.\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function MultiInputPolicy.__init__ at 0x7a3d089949a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a3d08983400>"}, "verbose": 1, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1760763312620457247, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-1.22841     0.21497735  0.07748517]\n [-1.0206103  -1.2185386   0.07748652]\n [ 0.72022736 -0.8737733   0.07747305]\n [-0.30107504  0.288914    0.0774821 ]]", "desired_goal": "[[ 0.36112392  0.17634115  1.096211  ]\n [ 0.24654493  0.8519841  -1.0753653 ]\n [ 0.9241863  -0.9614184   0.9792167 ]\n [ 1.4680223   1.1964501   1.6995735 ]]", "observation": "[[ 8.1903350e-01 -1.5916234e+00 -1.0355302e+00  4.8066604e-01\n  -5.6455927e-03 -1.9051181e-02  1.0440358e+00 -1.2284100e+00\n   2.1497735e-01  7.7485166e-02 -1.2431941e-03  7.4064187e-03\n  -7.3137465e-03  4.9841408e-02  5.3002536e-03  3.5884127e-02\n  -2.9878113e-03 -6.0057766e-03  3.6642880e-03]\n [-1.1180477e-01  3.6763445e-02  4.2043820e-01 -7.4854606e-01\n   6.1243820e-01  1.8104994e+00 -1.1248100e+00 -1.0206103e+00\n  -1.2185386e+00  7.7486522e-02 -1.3883171e-03  7.1634217e-03\n  -8.4401639e-03  4.9815588e-02  4.9523055e-03  3.6471937e-02\n  -1.8438983e-03 -7.1523814e-03  3.3158229e-03]\n [ 2.6877752e-01 -1.4341365e-01 -4.5159675e-02  5.1730669e-01\n  -2.1579850e+00  2.2839868e+00  1.0466014e+00  7.2022736e-01\n  -8.7377328e-01  7.7473052e-02 -1.2136886e-03  7.5690136e-03\n  -7.9945559e-03  5.0655846e-02  4.1805613e-03  3.6230877e-02\n   2.4649274e-04 -4.4204802e-03  4.2749229e-03]\n [ 1.0988108e+00 -2.2458230e-01 -1.0394250e+00  4.5175353e-01\n   1.4150310e+00 -6.1593980e-02 -1.1247891e+00 -3.0107504e-01\n   2.8891400e-01  7.7482097e-02 -1.2730256e-03  7.2372453e-03\n  -8.8396622e-03  4.9885653e-02  4.3727886e-03  3.6178038e-02\n   1.4142576e-04 -4.0141563e-03  3.1020730e-03]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.1362879   0.02174678  0.01998976]\n [-0.11413451 -0.12639943  0.01998981]\n [ 0.07145511 -0.09076978  0.0199894 ]\n [-0.0374253   0.02938773  0.01998967]]", "desired_goal": "[[ 0.03147329  0.01508628  0.16440853]\n [ 0.02153436  0.07355513  0.02      ]\n [ 0.08031504 -0.08337326  0.15662849]\n [ 0.12748905  0.10336456  0.20453179]]", "observation": "[[ 9.1734312e-02 -4.0247214e-01  7.7497778e-03  3.5547987e-02\n   4.6066485e-02  2.3852637e-02  7.9762131e-02 -1.3628790e-01\n   2.1746777e-02  1.9989764e-02  1.8927873e-05  5.0990920e-06\n   3.7329859e-04 -2.6726571e-05  4.1854826e-05 -2.0083484e-05\n  -1.8802858e-03 -1.1934903e-03  1.3668372e-04]\n [-2.1340416e-01  1.1896842e-01  3.4815910e-01 -3.7102857e-01\n   3.0056581e-01  8.1123072e-01  1.0653784e-07 -1.1413451e-01\n  -1.2639943e-01  1.9989805e-02 -7.4845884e-06 -2.2688648e-05\n  -6.8077461e-05 -2.8612207e-05  1.8605071e-05  2.0082765e-05\n  -1.1929304e-03 -1.8806076e-03 -2.9793309e-04]\n [-8.8645324e-02  6.1272278e-02  2.3930107e-01  4.7667317e-02\n  -8.4017074e-01  1.0150040e+00  7.9856485e-02  7.1455106e-02\n  -9.0769775e-02  1.9989397e-02  2.4297900e-05  2.3692506e-05\n   1.0652987e-04  3.2759133e-05 -3.2962533e-05  3.6105332e-06\n   6.3145519e-05 -2.4348134e-04  8.9828676e-04]\n [ 1.8344823e-01  3.5280526e-02  6.8391724e-03  2.5984824e-02\n   6.3103765e-01  5.5436241e-03  8.7081247e-07 -3.7425302e-02\n   2.9387733e-02  1.9989671e-02  1.3498514e-05 -1.4246601e-05\n  -2.2461711e-04 -2.3494806e-05 -2.0117981e-05  1.2986452e-11\n   1.2789323e-08  1.3500625e-08 -5.6452869e-04]]"}, "_episode_num": 20694, "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYiJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="}, "_n_updates": 249975, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': dict[str, tuple[int, ...]], 'observations': dict[str, numpy.ndarray], 'next_observations': dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function DictReplayBuffer.__init__ at 0x7a3d08da6520>", "add": "<function DictReplayBuffer.add at 0x7a3d08da6660>", "sample": "<function DictReplayBuffer.sample at 0x7a3d08da6700>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7a3d08da67a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a3d08d36d00>"}, "replay_buffer_kwargs": {}, "n_steps": 1, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -4.0, "ent_coef": "auto", "target_update_interval": 1, "top_quantiles_to_drop_per_net": 2, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "{'achieved_goal': Box(-10.0, 10.0, (3,), float32), 'desired_goal': Box(-10.0, 10.0, (3,), float32), 'observation': Box(-10.0, 10.0, (19,), float32)}", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "bounded_below": "[ True  True  True  True]", "high": "[1. 1. 1. 1.]", "bounded_above": "[ True  True  True  True]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 4, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "1.2.1", "OpenAI Gym": "0.25.2"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1769acfa46f3f955cdcf2b0f2ff0a1aa49cd96996ac791bf63f7b9ddb5243366
-size 665877
+oid sha256:afbbc924e65a1a9a421b747f8e9abbfb41592923e4246422bc4c39d5c35906d7
+size 636222

results.json

@@ -1 +1 @@
-{"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-18T01:40:28.168984"}
+{"mean_reward": -48.267, "std_reward": 8.995649559648262, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-10-18T07:21:35.506482"}

tqc-PandaPickAndPlace-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0b859d8a7e2038c52e147d35719b24a424e5245483ab60e55e0a44e4773a6d
-size 3503520
+oid sha256:1303e9141002c3dbd29f626cb04af263db0d1885b9896281408e8f2dba7d8109
+size 3503376

tqc-PandaPickAndPlace-v3/actor.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a645c9d3c60daef407eb9c9486f3362eaaa04fa46e3c7448538cc8728c6e89
+oid sha256:48af5651b38885c47918540efbbfbcd8d422b4b9261c5d60416995f24b7dfeee
 size 603099

tqc-PandaPickAndPlace-v3/critic.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d00a7f2c4a5623b0f846ba3f643d379e8ef090b555e51874bc1851f92eff7ae
+oid sha256:29846be5f47eb0bb9f5e9454fc56dda219399aab62ad80794ef4284a4344e877
 size 1288311

tqc-PandaPickAndPlace-v3/data

@@ -4,28 +4,28 @@
         ":serialized:": "gAWVMQAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
         "__module__": "sb3_contrib.tqc.policies",
         "__doc__": "\n    Policy class (with both actor and critic) for TQC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n    :param features_extractor_class: Features extractor to use.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    :param n_quantiles: Number of quantiles for the critic.\n    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
-        "__init__": "<function MultiInputPolicy.__init__ at 0x7ffa471a2de0>",
+        "__init__": "<function MultiInputPolicy.__init__ at 0x7a3d089949a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ffa46fb2f40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7a3d08983400>"
     },
     "verbose": 1,
     "policy_kwargs": {
         "use_sde": false
     },
-    "num_timesteps": 100000,
-    "_total_timesteps": 100000,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1760750075408543266,
+    "start_time": 1760763312620457247,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "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",
-        "achieved_goal": "[[ 0.45666164  0.7468795   0.13633364]\n [ 1.2482401  -0.6034163   0.10520676]\n [-0.41451776  0.70816296  0.13633144]\n [ 0.219276   -0.28775188  0.13634379]]",
-        "desired_goal": "[[-1.7296052  -1.6431981  -0.8150811 ]\n [-0.91172874 -0.47376338 -0.7072949 ]\n [ 0.67768896  0.14283045  1.4594789 ]\n [-1.7110527   0.79149896 -0.477671  ]]",
-        "observation": "[[ 7.29185402e-01  9.97959197e-01 -3.38843353e-02 -2.00835988e-01\n   1.54472518e+00 -2.66674209e+00 -1.05770171e+00  4.56661642e-01\n   7.46879518e-01  1.36333644e-01 -3.57736135e-03  3.18802940e-03\n  -9.85643361e-03  5.48287891e-02  4.12563095e-03  6.32412657e-02\n  -2.75559979e-03 -1.37450555e-02 -1.23619894e-03]\n [ 1.13952637e+00  5.62435329e-01 -3.58537883e-01  2.36037278e+00\n  -7.13179052e-01  4.69735771e-01  9.53502119e-01  1.24824011e+00\n  -6.03416324e-01  1.05206758e-01  9.28858742e-02 -4.68555123e-01\n   3.61620098e-01  8.16140652e+00 -5.53006983e+00  7.19821095e-01\n  -1.86530030e+00  3.51959014e+00 -2.92868048e-01]\n [ 7.55450487e-01  8.27823877e-01 -8.47191587e-02 -1.17728436e+00\n   1.76338172e+00 -2.22938991e+00 -9.37435687e-01 -4.14517760e-01\n   7.08162963e-01  1.36331439e-01 -3.45642050e-03  3.35177802e-03\n  -9.85575747e-03  5.45598976e-02  4.33983700e-03  6.33124262e-02\n  -4.00712574e-03 -1.51818888e-02 -1.22861471e-03]\n [ 6.46964192e-01  6.38084337e-02 -4.51891482e-01 -6.95268929e-01\n  -1.97337341e+00  2.59410050e-02  8.59932363e-01  2.19275996e-01\n  -2.87751883e-01  1.36343792e-01 -3.57513549e-03  3.34800081e-03\n   1.10912776e+00  5.45607135e-02  4.08879062e-03  6.30674660e-02\n  -2.56768614e-03 -1.51774874e-02 -1.22860912e-03]]"
+        ":serialized:": "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",
+        "achieved_goal": "[[-1.22841     0.21497735  0.07748517]\n [-1.0206103  -1.2185386   0.07748652]\n [ 0.72022736 -0.8737733   0.07747305]\n [-0.30107504  0.288914    0.0774821 ]]",
+        "desired_goal": "[[ 0.36112392  0.17634115  1.096211  ]\n [ 0.24654493  0.8519841  -1.0753653 ]\n [ 0.9241863  -0.9614184   0.9792167 ]\n [ 1.4680223   1.1964501   1.6995735 ]]",
+        "observation": "[[ 8.1903350e-01 -1.5916234e+00 -1.0355302e+00  4.8066604e-01\n  -5.6455927e-03 -1.9051181e-02  1.0440358e+00 -1.2284100e+00\n   2.1497735e-01  7.7485166e-02 -1.2431941e-03  7.4064187e-03\n  -7.3137465e-03  4.9841408e-02  5.3002536e-03  3.5884127e-02\n  -2.9878113e-03 -6.0057766e-03  3.6642880e-03]\n [-1.1180477e-01  3.6763445e-02  4.2043820e-01 -7.4854606e-01\n   6.1243820e-01  1.8104994e+00 -1.1248100e+00 -1.0206103e+00\n  -1.2185386e+00  7.7486522e-02 -1.3883171e-03  7.1634217e-03\n  -8.4401639e-03  4.9815588e-02  4.9523055e-03  3.6471937e-02\n  -1.8438983e-03 -7.1523814e-03  3.3158229e-03]\n [ 2.6877752e-01 -1.4341365e-01 -4.5159675e-02  5.1730669e-01\n  -2.1579850e+00  2.2839868e+00  1.0466014e+00  7.2022736e-01\n  -8.7377328e-01  7.7473052e-02 -1.2136886e-03  7.5690136e-03\n  -7.9945559e-03  5.0655846e-02  4.1805613e-03  3.6230877e-02\n   2.4649274e-04 -4.4204802e-03  4.2749229e-03]\n [ 1.0988108e+00 -2.2458230e-01 -1.0394250e+00  4.5175353e-01\n   1.4150310e+00 -6.1593980e-02 -1.1247891e+00 -3.0107504e-01\n   2.8891400e-01  7.7482097e-02 -1.2730256e-03  7.2372453e-03\n  -8.8396622e-03  4.9885653e-02  4.3727886e-03  3.6178038e-02\n   1.4142576e-04 -4.0141563e-03  3.1020730e-03]]"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -33,25 +33,25 @@
     },
     "_last_original_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "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",
-        "achieved_goal": "[[ 0.04540964  0.09857238  0.01998945]\n [ 0.13585801 -0.07886199  0.01838389]\n [-0.0541342   0.09348487  0.01998934]\n [ 0.01828517 -0.0373824   0.01998997]]",
-        "desired_goal": "[[-0.14761657 -0.14368674  0.0367117 ]\n [-0.07740058 -0.03983729  0.04381718]\n [ 0.05905344  0.01491816  0.18665504]\n [-0.1460238   0.07252194  0.05895443]]",
-        "observation": "[[ 7.75068300e-03  1.00793801e-01  8.64082575e-02 -2.22494066e-01\n   5.86150467e-01 -1.22808981e+00  5.44464728e-03  4.54096422e-02\n   9.85723808e-02  1.99894495e-02  9.27750392e-08 -2.78913903e-05\n  -1.12769812e-05  2.56027215e-05  4.93884045e-06  2.08185666e-05\n  -2.24239382e-04  1.27332902e-03 -1.32319146e-05]\n [ 1.11389987e-01 -3.80641930e-02  3.75008211e-02  8.29971611e-01\n  -4.20223355e-01  1.67505682e-01  7.46387392e-02  1.35858014e-01\n  -7.88619891e-02  1.83838885e-02  2.63987854e-02 -8.03775415e-02\n   2.14769155e-01  7.71854997e-01 -6.18014753e-01  7.42464811e-02\n  -1.81408465e+00  3.13239479e+00 -5.08441925e-01]\n [ 1.43844215e-02  4.65495996e-02  7.87502453e-02 -6.23741508e-01\n   6.83608234e-01 -1.03348720e+00  9.58231650e-03 -5.41342013e-02\n   9.34848711e-02  1.99893359e-02  3.31901865e-05 -9.05362785e-10\n  -1.08860195e-05  1.44836987e-09  2.88598549e-05  2.88628453e-05\n  -1.44305220e-03  5.61475240e-08 -9.64327729e-09]\n [-1.30158374e-02 -1.97041303e-01  2.34375689e-02 -4.25669104e-01\n  -9.81906414e-01 -2.99635772e-02  7.14195371e-02  1.82851721e-02\n  -3.73823978e-02  1.99899729e-02  7.01928968e-07 -6.44282920e-07\n   6.46963418e-01  7.91315102e-08  8.24747872e-07  1.17060495e-06\n  -4.12374357e-05  3.95657844e-06 -2.70655911e-11]]"
+        ":serialized:": "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",
+        "achieved_goal": "[[-0.1362879   0.02174678  0.01998976]\n [-0.11413451 -0.12639943  0.01998981]\n [ 0.07145511 -0.09076978  0.0199894 ]\n [-0.0374253   0.02938773  0.01998967]]",
+        "desired_goal": "[[ 0.03147329  0.01508628  0.16440853]\n [ 0.02153436  0.07355513  0.02      ]\n [ 0.08031504 -0.08337326  0.15662849]\n [ 0.12748905  0.10336456  0.20453179]]",
+        "observation": "[[ 9.1734312e-02 -4.0247214e-01  7.7497778e-03  3.5547987e-02\n   4.6066485e-02  2.3852637e-02  7.9762131e-02 -1.3628790e-01\n   2.1746777e-02  1.9989764e-02  1.8927873e-05  5.0990920e-06\n   3.7329859e-04 -2.6726571e-05  4.1854826e-05 -2.0083484e-05\n  -1.8802858e-03 -1.1934903e-03  1.3668372e-04]\n [-2.1340416e-01  1.1896842e-01  3.4815910e-01 -3.7102857e-01\n   3.0056581e-01  8.1123072e-01  1.0653784e-07 -1.1413451e-01\n  -1.2639943e-01  1.9989805e-02 -7.4845884e-06 -2.2688648e-05\n  -6.8077461e-05 -2.8612207e-05  1.8605071e-05  2.0082765e-05\n  -1.1929304e-03 -1.8806076e-03 -2.9793309e-04]\n [-8.8645324e-02  6.1272278e-02  2.3930107e-01  4.7667317e-02\n  -8.4017074e-01  1.0150040e+00  7.9856485e-02  7.1455106e-02\n  -9.0769775e-02  1.9989397e-02  2.4297900e-05  2.3692506e-05\n   1.0652987e-04  3.2759133e-05 -3.2962533e-05  3.6105332e-06\n   6.3145519e-05 -2.4348134e-04  8.9828676e-04]\n [ 1.8344823e-01  3.5280526e-02  6.8391724e-03  2.5984824e-02\n   6.3103765e-01  5.5436241e-03  8.7081247e-07 -3.7425302e-02\n   2.9387733e-02  1.9989671e-02  1.3498514e-05 -1.4246601e-05\n  -2.2461711e-04 -2.3494806e-05 -2.0117981e-05  1.2986452e-11\n   1.2789323e-08  1.3500625e-08 -5.6452869e-04]]"
     },
-    "_episode_num": 2080,
+    "_episode_num": 20694,
     "use_sde": false,
     "sde_sample_freq": -1,
     "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwEkAAAAAAACMAWyUSzKMAXSUR0CW/KXOnl4kdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CW/y+ERJ2/dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXB2KoybhFdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXBwxvegtfdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXCGsJIDoydX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXCun3cpLFdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXE6WZJCjUdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXE3U8V58jdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXFPifxtpFdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXGZ3EQ5FPdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXItx2B8QadX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXIo73PAwgdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXI+9RaX8gdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXJm+5e7cxdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXLsEhaC+UdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXLnkMTewcdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXL9iRnvlVdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXMnvdM0xedX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXOqSh8IAwdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXOk+b3Gn5dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXO690zTF3dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXPi3Q2MsIdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXRislsxfwdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXRftix3V1dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXR3sWfseGdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXS/JUYKpldX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXVXywfQrudX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXVSXdj5KwdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXVoYnv2GqdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXWQ1V5rxidX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXYUwj+rEMdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXYPKEWZZ0dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXYlEv0yxidX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXZMqptJnQdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXbNLwWnCPdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXbH0Re1KHdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXbeArxy4ndX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXcKacqe9SdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXeSWI42jxdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXeOogmqo7dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXenJJGvwFdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXfxJSBK+SdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXiOoC+10DdX2UKGgGRwAAAAAAAAAAaAdLAWgIR0CXiSTEBKcvdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXiJVC5VfedX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXife9Ba9sdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXjMElme18dX2UKGgGRwAAAAAAAAAAaAdLAWgIR0CXjP7wrlNldX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXlWxEORT1dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXlNvx6OYIdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXljU7Sy+pdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXmQ6DXe3ydX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXoUYsunMudX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXoLVjI7vHdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXohIxxkupdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXpLn7pFCtdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXrUQE6kqMdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXrLT0xubadX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXri8WbgCPdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXs0kjHGS7dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXvFHVf/m1dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXu8G8274BdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXvS5wOvt/dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXv/gam4y5dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXyBc8TzundX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXx4kNWluWdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXyOOYplSTdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CXy7HdGiHqdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX1BuYx+KCdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX04tknTiLdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX1OT/yXlbdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX14ySFGoadX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX4A/p+tr9dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX34JAt4A0dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX4PUSIxgzdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX5d+5vtMPdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX72RkEs8QdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX7tSDAaegdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX8DHVwxWUdX2UKGgGRwAAAAAAAAAAaAdLAWgIR0CX7xEd/8VIdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX8xmv4dp7dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX+0pCKJl8dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX/BXFLnLadX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX+vj0cwQEdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CX/sjU/fO2dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYBxZKWcBmdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYB97YkE9udX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYBr4jKPn0dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYCrKfFrEcdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYEruVopQUdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYE5yJKraNdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYEoOMVDa5dX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYGIWYnfEXdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYIj9ic5KfdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYIwqNIbwSdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYIespXp4bdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYJgnXNC7cdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYLllfZ26kdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYLyIldC3PdX2UKGgGR8BJAAAAAAAAaAdLMmgIR0CYLgVI7NjcdWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiImJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="
+        ":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKImJiYmJiYmJiYmJiYmJiYmJiYmJiYiJiYmJiYmJiYmJiYmJiYmJiYmJiYmIiYmJiYmIiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYmJiYllLg=="
     },
-    "_n_updates": 24975,
+    "_n_updates": 249975,
     "buffer_size": 1000000,
     "batch_size": 256,
     "learning_starts": 100,
@@ -65,12 +65,12 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': dict[str, tuple[int, ...]], 'observations': dict[str, numpy.ndarray], 'next_observations': dict[str, numpy.ndarray]}",
         "__doc__": "\n    Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n    Extends the ReplayBuffer to use dictionary observations\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        Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
-        "__init__": "<function DictReplayBuffer.__init__ at 0x7ffa475cc900>",
-        "add": "<function DictReplayBuffer.add at 0x7ffa475cca40>",
-        "sample": "<function DictReplayBuffer.sample at 0x7ffa475ccae0>",
-        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7ffa475ccb80>",
+        "__init__": "<function DictReplayBuffer.__init__ at 0x7a3d08da6520>",
+        "add": "<function DictReplayBuffer.add at 0x7a3d08da6660>",
+        "sample": "<function DictReplayBuffer.sample at 0x7a3d08da6700>",
+        "_get_samples": "<function DictReplayBuffer._get_samples at 0x7a3d08da67a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ffa47579e80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7a3d08d36d00>"
     },
     "replay_buffer_kwargs": {},
     "n_steps": 1,
@@ -93,7 +93,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             4

tqc-PandaPickAndPlace-v3/ent_coef_optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c9c1851299a06c166bddcb0a60f894ee54a3f6a0d4f8359e5d47c1b4a62bfa
+oid sha256:e666dc75ff016a14db7c0e42ab3863f165ea8529a568866057baac74aec1e274
 size 2401

tqc-PandaPickAndPlace-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03564a84fd2cb34afa6e6328e86b6fef8f035f7fdcc650e600c711ebd038428b
+oid sha256:4c983fd0caeebd4d4b8db4799af572e5dbcef2b67045a634c0132c425f7a8a99
 size 1588163

tqc-PandaPickAndPlace-v3/pytorch_variables.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0307de67181d43315fe973c1b06b504b991db07588fe1b56d15d401a62d08681
+oid sha256:8bbef1fb4f2f3aa4a7ae6fae369244daa05d8d2c44237bd18c53eb800362a585
 size 1577

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d4f9b7e395e9a9e5c948d973e4e95fac2589e2ecefd5fc2739f72758fbb8d4
-size 3472
+oid sha256:57d747b24762a7af6e7e712889a452e677a0f3860da530eb24394b4010e397ca
+size 3473