Upload PPO LunarLander-v2 trained agent 1M steps
Browse files- .gitattributes +1 -0
- README.md +28 -0
- config.json +1 -0
- ppo-LunarLander-v2.zip +3 -0
- ppo-LunarLander-v2/_stable_baselines3_version +1 -0
- ppo-LunarLander-v2/data +94 -0
- ppo-LunarLander-v2/policy.optimizer.pth +3 -0
- ppo-LunarLander-v2/policy.pth +3 -0
- ppo-LunarLander-v2/pytorch_variables.pth +3 -0
- ppo-LunarLander-v2/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- LunarLander-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: PPO
|
10 |
+
results:
|
11 |
+
- metrics:
|
12 |
+
- type: mean_reward
|
13 |
+
value: 267.56 +/- 15.74
|
14 |
+
name: mean_reward
|
15 |
+
task:
|
16 |
+
type: reinforcement-learning
|
17 |
+
name: reinforcement-learning
|
18 |
+
dataset:
|
19 |
+
name: LunarLander-v2
|
20 |
+
type: LunarLander-v2
|
21 |
+
---
|
22 |
+
|
23 |
+
# **PPO** Agent playing **LunarLander-v2**
|
24 |
+
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
+
|
26 |
+
## Usage (with Stable-baselines3)
|
27 |
+
TODO: Add your code
|
28 |
+
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7f5bdd64f0e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5bdd64f170>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5bdd64f200>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5bdd64f290>", "_build": "<function ActorCriticPolicy._build at 0x7f5bdd64f320>", "forward": "<function ActorCriticPolicy.forward at 0x7f5bdd64f3b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5bdd64f440>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5bdd64f4d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5bdd64f560>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5bdd64f5f0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5bdd64f680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f5bdd6a71b0>"}, "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:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651684615.4509566, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVXhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIKxa/KWyVcECUhpRSlIwBbJRNOwGMAXSUR0CirS5QP7N0dX2UKGgGaAloD0MIJjeKrDXwcECUhpRSlGgVTTUBaBZHQKKte+Yc/+t1fZQoaAZoCWgPQwhXI7vSsmVwQJSGlFKUaBVL9GgWR0Cira0rbxmTdX2UKGgGaAloD0MI+8xZn3KXZkCUhpRSlGgVTegDaBZHQKKtxabnX/Z1fZQoaAZoCWgPQwiHhzB+WptxQJSGlFKUaBVNSAFoFkdAoq3dvhqCYnV9lChoBmgJaA9DCPz+zYsTdXFAlIaUUpRoFU0WAWgWR0CirmT4L1EmdX2UKGgGaAloD0MIETenkgHNb0CUhpRSlGgVS/JoFkdAoq6/VI7NjnV9lChoBmgJaA9DCGlSCrr9O3JAlIaUUpRoFU3UAWgWR0CiruP4dp7DdX2UKGgGaAloD0MIxsN7DmxKc0CUhpRSlGgVS/doFkdAoq763d9DyHV9lChoBmgJaA9DCDdxcr9DTXBAlIaUUpRoFU0yAWgWR0Cir1Dej2zwdX2UKGgGaAloD0MIu0OKARLBb0CUhpRSlGgVTQEBaBZHQKKvieJYT0x1fZQoaAZoCWgPQwiCjevfdTFyQJSGlFKUaBVL+GgWR0CisE070WdmdX2UKGgGaAloD0MIZqGd06xLbUCUhpRSlGgVS/VoFkdAorFTIPsiS3V9lChoBmgJaA9DCBA7U+i8G3JAlIaUUpRoFU1cAWgWR0CisZMtK7I1dX2UKGgGaAloD0MIU+knnF0jckCUhpRSlGgVTRIBaBZHQKKx5mA9V3l1fZQoaAZoCWgPQwiT5Lm+D5VtQJSGlFKUaBVNBwFoFkdAorHnCZWq+HV9lChoBmgJaA9DCNZVgVrMfnJAlIaUUpRoFU0sAWgWR0Cise5NoJzDdX2UKGgGaAloD0MI8RKc+sBobkCUhpRSlGgVS/doFkdAorITDl5nlHV9lChoBmgJaA9DCOsdbofGSnJAlIaUUpRoFUv+aBZHQKKyYq8UVSJ1fZQoaAZoCWgPQwjKUBVTqSVyQJSGlFKUaBVNFQFoFkdAorJxAUtZm3V9lChoBmgJaA9DCG2oGOcvRXFAlIaUUpRoFUv5aBZHQKKyzZmqYJF1fZQoaAZoCWgPQwjqr1dYcKluQJSGlFKUaBVNBgFoFkdAorOjZlFtsXV9lChoBmgJaA9DCF2lu+vscXFAlIaUUpRoFU0gAWgWR0CitAcU21lYdX2UKGgGaAloD0MIswbvqzJ5cECUhpRSlGgVTQsBaBZHQKK0bvhIe5p1fZQoaAZoCWgPQwjqy9JOjfhxQJSGlFKUaBVNGQFoFkdAorRuICU5dXV9lChoBmgJaA9DCBt/orLhEHBAlIaUUpRoFU0jAWgWR0CitdIk7fYSdX2UKGgGaAloD0MIWtb9Y+H4ckCUhpRSlGgVS/ZoFkdAoratv/BFeHV9lChoBmgJaA9DCFlQGJRp6HBAlIaUUpRoFUv/aBZHQKK3EG5c1O11fZQoaAZoCWgPQwh9sIwN3ZVuQJSGlFKUaBVNIwFoFkdAorcMHObAlHV9lChoBmgJaA9DCGN6whJP13BAlIaUUpRoFU0ZAWgWR0CitxcOkLx7dX2UKGgGaAloD0MIUiY1tIFJbUCUhpRSlGgVS+9oFkdAorcnNX5nDnV9lChoBmgJaA9DCGbAWUoWWXFAlIaUUpRoFUv2aBZHQKK3OHhS9/V1fZQoaAZoCWgPQwiCN6RRwfNyQJSGlFKUaBVNHgFoFkdAord36be/H3V9lChoBmgJaA9DCJ/kDptIlW9AlIaUUpRoFU0xAWgWR0Cit86t9x6wdX2UKGgGaAloD0MIvsEXJhOwcECUhpRSlGgVTRABaBZHQKK4IEOAiFF1fZQoaAZoCWgPQwiWzodnCYpyQJSGlFKUaBVNCgFoFkdAorjVyYG+snV9lChoBmgJaA9DCCDT2jR203BAlIaUUpRoFUv4aBZHQKK44Yu01Il1fZQoaAZoCWgPQwhy3CkdLOFtQJSGlFKUaBVNEgFoFkdAorm0lHBk7XV9lChoBmgJaA9DCJwVURM9+nJAlIaUUpRoFU0VAWgWR0CiucGhmGucdX2UKGgGaAloD0MIyGDFqdYNb0CUhpRSlGgVS+5oFkdAort+BQN1AHV9lChoBmgJaA9DCLth26JM1HJAlIaUUpRoFU0HAWgWR0Ciu7Ay2x6fdX2UKGgGaAloD0MIvHoVGZ0RcECUhpRSlGgVS+BoFkdAoruvalDWsnV9lChoBmgJaA9DCB3mywswY3FAlIaUUpRoFUv2aBZHQKK7xosZpBZ1fZQoaAZoCWgPQwhwl/26E39wQJSGlFKUaBVL/GgWR0Ciu8o8p1A8dX2UKGgGaAloD0MItTS3QpiVcUCUhpRSlGgVTREBaBZHQKK8ZC/oJRh1fZQoaAZoCWgPQwgY6rDCrTNvQJSGlFKUaBVL/mgWR0CiyorMkhRqdX2UKGgGaAloD0MIqkNuhhtUcECUhpRSlGgVS+9oFkdAosqdH8TBZnV9lChoBmgJaA9DCFs//WfNPHBAlIaUUpRoFU00AWgWR0CiytPJA+pwdX2UKGgGaAloD0MIJctJKH1ZcECUhpRSlGgVTRIBaBZHQKLMCiosI3R1fZQoaAZoCWgPQwgfMA+ZssdwQJSGlFKUaBVNGgFoFkdAosw+lGgBcXV9lChoBmgJaA9DCAJmvoNfx3FAlIaUUpRoFU0LAWgWR0CizOStmthedX2UKGgGaAloD0MI+BisONWCbUCUhpRSlGgVTRwBaBZHQKLNUkY4yXV1fZQoaAZoCWgPQwhHHLKBdA5xQJSGlFKUaBVL6mgWR0Cizm1S4vvjdX2UKGgGaAloD0MIjpPCvMdvb0CUhpRSlGgVS/5oFkdAos6Wcz67/XV9lChoBmgJaA9DCK7VHvZCNWdAlIaUUpRoFU3oA2gWR0Cizt1IiC8OdX2UKGgGaAloD0MIdeWzPE8NcECUhpRSlGgVTQcBaBZHQKLPBRIBikR1fZQoaAZoCWgPQwhosKnz6ItzQJSGlFKUaBVNFAFoFkdAos9lxEORT3V9lChoBmgJaA9DCPeUnBO7hHBAlIaUUpRoFU0dAWgWR0Ciz4GoBJZodX2UKGgGaAloD0MImxw+6cTzZUCUhpRSlGgVTegDaBZHQKLQB7FbVz91fZQoaAZoCWgPQwjf4uE9B4pyQJSGlFKUaBVNFgFoFkdAotASL2pQ13V9lChoBmgJaA9DCM0FLo+1eHFAlIaUUpRoFU0UAWgWR0Ci0EZRKpT/dX2UKGgGaAloD0MI0R+aefKycECUhpRSlGgVS9hoFkdAotCZyXD3unV9lChoBmgJaA9DCGggls1ctnFAlIaUUpRoFU0aAWgWR0Ci0KIQe3hGdX2UKGgGaAloD0MIsRafAuDEc0CUhpRSlGgVS95oFkdAotDhUBGQS3V9lChoBmgJaA9DCIlhhzFpF3JAlIaUUpRoFU1FAWgWR0Ci0Sm5c1O1dX2UKGgGaAloD0MI5BBxc6p+cUCUhpRSlGgVTSgBaBZHQKLSqdWhh6V1fZQoaAZoCWgPQwjO4sXCUARyQJSGlFKUaBVNFAFoFkdAotKqsr/bTXV9lChoBmgJaA9DCM5vmGiQl3BAlIaUUpRoFUv7aBZHQKLTJnBciW51fZQoaAZoCWgPQwgVONkG7plyQJSGlFKUaBVL+GgWR0Ci0zpb2USqdX2UKGgGaAloD0MI05/9SFE0ckCUhpRSlGgVTQ4BaBZHQKLT4KwY+B91fZQoaAZoCWgPQwjfh4OEKM1xQJSGlFKUaBVL+WgWR0Ci0+02LpA2dX2UKGgGaAloD0MIKq2/JQBibUCUhpRSlGgVTQMBaBZHQKLUOPkq+al1fZQoaAZoCWgPQwhYjLrWXhRwQJSGlFKUaBVL92gWR0Ci1HqcNH6NdX2UKGgGaAloD0MIw5rKorAGcUCUhpRSlGgVS/ZoFkdAotR/q/ub7XV9lChoBmgJaA9DCHQK8rPRLnNAlIaUUpRoFU02AWgWR0Ci1LlMIu5CdX2UKGgGaAloD0MItOTxtPx+ckCUhpRSlGgVS/1oFkdAotUuM2m52HV9lChoBmgJaA9DCLHgfsADD3BAlIaUUpRoFU0VAWgWR0Ci1T2/ag27dX2UKGgGaAloD0MI2Ls/3qt4a0CUhpRSlGgVTRcBaBZHQKLV3OCXhOx1fZQoaAZoCWgPQwgQBwlRfvBwQJSGlFKUaBVNMgFoFkdAotYL2QGOdXV9lChoBmgJaA9DCLsnDws1iG9AlIaUUpRoFU0SAWgWR0Ci1hSzw+dLdX2UKGgGaAloD0MIyCb5ET8dZ0CUhpRSlGgVTegDaBZHQKLW4mx+rlx1fZQoaAZoCWgPQwiM1lHVxM9wQJSGlFKUaBVL+GgWR0Ci1yqABkqddX2UKGgGaAloD0MITfT5KCNiSkCUhpRSlGgVS9poFkdAotfYQjD8+HV9lChoBmgJaA9DCF2pZ0HobnJAlIaUUpRoFU0qAWgWR0Ci2CpeeFtbdX2UKGgGaAloD0MI/FBpxEzRcECUhpRSlGgVTRgBaBZHQKLZG1twaR91fZQoaAZoCWgPQwh0QBL2LVhxQJSGlFKUaBVNPQFoFkdAotkcf1YhdXV9lChoBmgJaA9DCHnJ/+RvenNAlIaUUpRoFU0EAWgWR0Ci2Va3iJfqdX2UKGgGaAloD0MIgUI9fQRScUCUhpRSlGgVTQsBaBZHQKLZypjMFEB1fZQoaAZoCWgPQwh8KNGSx7NvQJSGlFKUaBVL92gWR0Ci2fhF/hESdX2UKGgGaAloD0MInrEv2TjlcECUhpRSlGgVTSoBaBZHQKLaHcIJJGx1fZQoaAZoCWgPQwib6PNRhpNxQJSGlFKUaBVNRQFoFkdAotpV2Rq46XV9lChoBmgJaA9DCBr8/WI29WxAlIaUUpRoFU0aAWgWR0Ci2oOk+HJtdX2UKGgGaAloD0MIzEV8J2ZWckCUhpRSlGgVS/poFkdAotqm2oegc3V9lChoBmgJaA9DCGA7GLEPcXBAlIaUUpRoFU2fAWgWR0Ci2vwKBun/dX2UKGgGaAloD0MIym37HrUHckCUhpRSlGgVTQUBaBZHQKLbCnfl6qt1fZQoaAZoCWgPQwgcX3tmSYxyQJSGlFKUaBVNBgFoFkdAotsHAj6eoXV9lChoBmgJaA9DCF3g8ljzhXFAlIaUUpRoFU0RAWgWR0Ci3Ek0iyIIdX2UKGgGaAloD0MISzlf7D0wbkCUhpRSlGgVTQIBaBZHQKLcpmjj7yh1fZQoaAZoCWgPQwjzVfKxO4pyQJSGlFKUaBVL/GgWR0Ci3NYvvjOtdX2UKGgGaAloD0MIJXhDGtXgcECUhpRSlGgVS/9oFkdAot3GGCZnc3VlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 372, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}
|
ppo-LunarLander-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:641fc2eba737f5477fc98cae627ac91cc6fa517f2cbc8f7fc939e6f82b27a547
|
3 |
+
size 143922
|
ppo-LunarLander-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.5.0
|
ppo-LunarLander-v2/data
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
|
5 |
+
"__module__": "stable_baselines3.common.policies",
|
6 |
+
"__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 ",
|
7 |
+
"__init__": "<function ActorCriticPolicy.__init__ at 0x7f5bdd64f0e0>",
|
8 |
+
"_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5bdd64f170>",
|
9 |
+
"reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5bdd64f200>",
|
10 |
+
"_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5bdd64f290>",
|
11 |
+
"_build": "<function ActorCriticPolicy._build at 0x7f5bdd64f320>",
|
12 |
+
"forward": "<function ActorCriticPolicy.forward at 0x7f5bdd64f3b0>",
|
13 |
+
"_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5bdd64f440>",
|
14 |
+
"_predict": "<function ActorCriticPolicy._predict at 0x7f5bdd64f4d0>",
|
15 |
+
"evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5bdd64f560>",
|
16 |
+
"get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5bdd64f5f0>",
|
17 |
+
"predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5bdd64f680>",
|
18 |
+
"__abstractmethods__": "frozenset()",
|
19 |
+
"_abc_impl": "<_abc_data object at 0x7f5bdd6a71b0>"
|
20 |
+
},
|
21 |
+
"verbose": 1,
|
22 |
+
"policy_kwargs": {},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float32",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.discrete.Discrete'>",
|
38 |
+
":serialized:": "gASVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
|
39 |
+
"n": 4,
|
40 |
+
"_shape": [],
|
41 |
+
"dtype": "int64",
|
42 |
+
"_np_random": null
|
43 |
+
},
|
44 |
+
"n_envs": 16,
|
45 |
+
"num_timesteps": 1015808,
|
46 |
+
"_total_timesteps": 1000000,
|
47 |
+
"_num_timesteps_at_start": 0,
|
48 |
+
"seed": null,
|
49 |
+
"action_noise": null,
|
50 |
+
"start_time": 1651684615.4509566,
|
51 |
+
"learning_rate": 0.0003,
|
52 |
+
"tensorboard_log": null,
|
53 |
+
"lr_schedule": {
|
54 |
+
":type:": "<class 'function'>",
|
55 |
+
":serialized:": "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"
|
56 |
+
},
|
57 |
+
"_last_obs": {
|
58 |
+
":type:": "<class 'numpy.ndarray'>",
|
59 |
+
":serialized:": "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"
|
60 |
+
},
|
61 |
+
"_last_episode_starts": {
|
62 |
+
":type:": "<class 'numpy.ndarray'>",
|
63 |
+
":serialized:": "gASVmAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSxCFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDEAAAAAAAAAAAAAAAAAAAAACUdJRiLg=="
|
64 |
+
},
|
65 |
+
"_last_original_obs": null,
|
66 |
+
"_episode_num": 0,
|
67 |
+
"use_sde": false,
|
68 |
+
"sde_sample_freq": -1,
|
69 |
+
"_current_progress_remaining": -0.015808000000000044,
|
70 |
+
"ep_info_buffer": {
|
71 |
+
":type:": "<class 'collections.deque'>",
|
72 |
+
":serialized:": "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"
|
73 |
+
},
|
74 |
+
"ep_success_buffer": {
|
75 |
+
":type:": "<class 'collections.deque'>",
|
76 |
+
":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
77 |
+
},
|
78 |
+
"_n_updates": 372,
|
79 |
+
"n_steps": 1024,
|
80 |
+
"gamma": 0.999,
|
81 |
+
"gae_lambda": 0.98,
|
82 |
+
"ent_coef": 0.01,
|
83 |
+
"vf_coef": 0.5,
|
84 |
+
"max_grad_norm": 0.5,
|
85 |
+
"batch_size": 64,
|
86 |
+
"n_epochs": 4,
|
87 |
+
"clip_range": {
|
88 |
+
":type:": "<class 'function'>",
|
89 |
+
":serialized:": "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"
|
90 |
+
},
|
91 |
+
"clip_range_vf": null,
|
92 |
+
"normalize_advantage": true,
|
93 |
+
"target_kl": null
|
94 |
+
}
|
ppo-LunarLander-v2/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96f9517de799c2bac5000663c02f2726b3471cfd3caa71735486095812093327
|
3 |
+
size 84893
|
ppo-LunarLander-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d3de4abc613aaad22c56abfa5ac9b85a6fd38a792873f3faea2d594c91195a8
|
3 |
+
size 43201
|
ppo-LunarLander-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
ppo-LunarLander-v2/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
|
2 |
+
Python: 3.7.13
|
3 |
+
Stable-Baselines3: 1.5.0
|
4 |
+
PyTorch: 1.11.0+cu113
|
5 |
+
GPU Enabled: True
|
6 |
+
Numpy: 1.21.6
|
7 |
+
Gym: 0.21.0
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:732d5bcc7bbe627b6450412534203a5a4f99e536442a73fef235216e52ade3b1
|
3 |
+
size 240587
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 267.5600490499961, "std_reward": 15.736758850376098, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-04T17:48:37.642759"}
|