Upload README.md with huggingface_hub

README.md

@@ -21,7 +21,7 @@ model-index:
       type: BreakoutNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 6.6 +/- 3.58
+      value: 416.7 +/- 149.94
       name: mean_reward
 ---
 
@@ -175,7 +175,9 @@ exp_config = {
             'n_evaluator_episode': 3,
             'manager': {
                 'shared_memory': False
-            }
+            },
+            'collect_max_episode_steps': 5000,
+            'eval_max_episode_steps': 20000
         },
         'policy': {
             'on_policy': False,
@@ -241,7 +243,7 @@ exp_config = {
             'root_noise_weight': 0.25,
             'random_collect_episode_num': 0,
             'eps': {
-                'eps_greedy_exploration_in_collect': False,
+                'eps_greedy_exploration_in_collect': True,
                 'type': 'linear',
                 'start': 1.0,
                 'end': 0.05,
@@ -290,7 +292,7 @@ exp_config = {
 - **Demo:** [video](https://huggingface.co/OpenDILabCommunity/BreakoutNoFrameskip-v4-MuZero/blob/main/replay.mp4)
 <!-- Provide the size information for the model. -->
 - **Parameters total size:** 24008.38 KB
-- **Last Update Date:** 2023-12-20
+- **Last Update Date:** 2023-12-26
 
 ## Environments
 <!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->