10_000_000 iterations

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 271.50 +/- 80.19
+      value: 614.50 +/- 224.56
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -25,48 +25,12 @@ This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)
+TODO: Add your code
 
-```python
-from stable_baselines3.common.env_util import make_atari_env
-from stable_baselines3.common.vec_env import VecFrameStack
-from stable_baselines3 import DQN
-from stable_baselines3.common.evaluation import evaluate_policy
-from huggingface_sb3 import load_from_hub, package_to_hub
-from stable_baselines3.common.utils import set_random_seed
-
-env_id = "SpaceInvadersNoFrameskip-v4"
-
-env = make_atari_env(env_id,
-                     n_envs=12,
-                     # Improving reproducibility
-                     seed=1)
-env = VecFrameStack(env, n_stack=4)  # Stack last four images
 
-# Improving reproducibility
-set_random_seed(42)
-
-# Using these parameters as default: https://huggingface.co/micheljperez/dqn-SpaceInvadersNoFrameskip-v4
-model = DQN(policy = "CnnPolicy",
-            env = env,
-            batch_size = 32,
-            buffer_size = 100_000,
-            exploration_final_eps = 0.01,
-            exploration_fraction = 0.025,
-            gradient_steps = 1,
-            learning_rate = 1e-4,
-            learning_starts = 100_000,
-            optimize_memory_usage = True,
-            replay_buffer_kwargs = {"handle_timeout_termination": False},
-            target_update_interval = 1000,
-            train_freq = 4,
-            # normalize = False,
-            tensorboard_log = "./tensorboard",
-            verbose=1
-           )
-           
-f = load_from_hub('masterdezign/dqn-SpaceInvadersNoFrameskip-v4', 'dqn-SpaceInvadersNoFrameskip-v4.zip')
-model = model.load(f)
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
 
-mean_reward, std_reward = evaluate_policy(model, env)
-print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
+...
 ```

dqn2-SpaceInvadersNoFrameskip-v4.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a779055156bda55a8d349d0461b011ad28ec05cd8f8f681fac399a7e6e5b8b6
+size 28089704

dqn2-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version

@@ -0,0 +1 @@
+1.6.0

dqn2-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e480362a02e6ca77eb5c7c331634f8efe5293bf6152117417f309d33967791fc
+size 13505611

dqn2-SpaceInvadersNoFrameskip-v4/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc1d694d02b4889415a5a64a80c97dd4ce56964ad8c9b6bea5fccf3a71a0c49
+size 13504937

dqn2-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

dqn2-SpaceInvadersNoFrameskip-v4/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.4.0-113-generic-x86_64-with-debian-buster-sid #127-Ubuntu SMP Wed May 18 14:30:56 UTC 2022
+Python: 3.7.13
+Stable-Baselines3: 1.6.0
+PyTorch: 1.12.0
+GPU Enabled: True
+Numpy: 1.21.5
+Gym: 0.21.0

results.json

@@ -1 +1 @@
-{"mean_reward": 271.5, "std_reward": 80.18883962248113, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-20T14:35:46.400659"}
+{"mean_reward": 614.5, "std_reward": 224.56012557887476, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-07-21T08:36:39.345391"}