Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -213.42 +/- 111.62
+      value: 109.93 +/- 52.00
       name: mean_reward
       verified: false
 ---
@@ -31,22 +31,22 @@ model-index:
   {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
 'env_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0005
 'seed': 1
-'total_timesteps': 300000
+'total_timesteps': 8388608
 'torch_deterministic': True
 'cuda': True
 'track': False
 'wandb_project_name': 'ppo-implementation-details'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 2048
-'num_steps': 1024
+'num_envs': 1024
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 256
+'num_minibatches': 128
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'SuperDan/ppo-lunar-sharedMLP'
-'batch_size': 2097152
-'minibatch_size': 8192}
+'batch_size': 262144
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1702250145.f982b9416d82.5070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4d97f0d8ca4096182f25d4122b28bc8d9bc931bf97c4e9e1b1bc223dd29e52
+size 727144

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88bcc5467c57ead0a38a64f0e057789b675891fc492cc2e68c6ecef2ffda2ce3
+oid sha256:f40d201d030a60ab8ae09d329af2b5ebb6ac7a096fea6f4915323169fa7b59d1
 size 1082216

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -213.41949862860216, "std_reward": 111.62084535750283, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-10T02:36:43.727016"}
+{"env_id": "LunarLander-v2", "mean_reward": 109.9289331221125, "std_reward": 51.99909361399946, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-11T02:10:12.815904"}