diff --git a/README.md b/README.md index 4e7907417b54b5764b862482dbc10097e16b0e22..ddf5b8630cedfd7b340772ad6362c805a0e08d52 100644 --- a/README.md +++ b/README.md @@ -36,7 +36,7 @@ push_to_hub( After identifying with the command : `huggingface-cli login` ## Weights & Biases -The run of the model is [here](https://wandb.ai/ghelfi/cartpole-training/runs/06exlpbm). +The run of the model is [here](https://wandb.ai/ghelfi/cartpole-training/runs/t95xgk54). Realized with the code below: ``` @@ -59,8 +59,7 @@ while True: if done: break -print("Mean Reward: ", np.mean(rewards)) -wandb.log({'reward_mean': np.mean(rewards)}) +wandb.log({'rewards': np.sum(rewards)}) ```