Update README.md

update eval results and continue training

README.md

@@ -15,7 +15,7 @@ model-index:
       type: nethack_challenge
     metrics:
     - type: mean_reward
-      value: 2228.00 +/- 0.00
+      value: 3245.47 +/- 2691.37
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r LLParallax/sample_factory_
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m <path.to.enjoy.module> --algo=APPO --env=nethack_challenge --train_dir=./train_dir --experiment=sample_factory_human_monk
+python -m sf_examples.nethack.enjoy_nethack --env=nethack_challenge --train_dir=./train_dir --experiment=sample_factory_human_monk
 ```
 
 
@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
 
 To continue training with this model, use the `train` script corresponding to this environment:
 ```
-python -m <path.to.train.module> --algo=APPO --env=nethack_challenge --train_dir=./train_dir --experiment=sample_factory_human_monk --restart_behavior=resume --train_for_env_steps=10000000000
+python -m sf_examples.nethack.train_nethack --env=nethack_challenge --character=mon-hum-neu-mal --num_workers=16 --num_envs_per_worker=32 batch_size=4096 --train_dir=./train_dir --experiment=sample_factory_human_monk --restart_behavior=resume --train_for_env_steps=10000000000
 ```
 
 Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.