diff --git a/README.md b/README.md index 3c9e45e491730e3f7dcbfd581d99bc05d716396b..773bba904c24b8eeeba9185443e9dfcc5ff57225 100644 --- a/README.md +++ b/README.md @@ -25,6 +25,4 @@ We finally have an evaluation with 100% of sucess: Here we set up a complete pipeline to solve Cartpole environment with A2C algorithm. -Wandb has been set up to follow the learning phase. -https://wandb.ai/maximecerise-ecl/cartpole-a2c - +Wandb has been set up to track the learning phase : [WandB tacking](https://wandb.ai/maximecerise-ecl/cartpole-a2c?nw=nwusermaximecerise) diff --git a/evaluate_reinforce_cartpole.py b/evaluate_reinforce_cartpole.py index 42f48985e181b66a9c169bdba2d8819398e49eeb..bf83fdec294598086e1b9fe3417dbc72d8c25c86 100644 --- a/evaluate_reinforce_cartpole.py +++ b/evaluate_reinforce_cartpole.py @@ -1,4 +1,4 @@ -import gym +import gymnasium as gym import torch import numpy as np import torch