Update README

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 497.72 +/- 0.79
+      value: 497.66 +/- 0.47
       name: Total reward (mean)
     task:
       type: reinforcement-learning
@@ -19,51 +19,69 @@ model-index:
       type: Isaac-Cartpole-v0
 ---
 
+<!-- ---
+torch: 497.66 +/- 0.47
+jax: 497.41 +/- 0.0
+numpy: 
+--- -->
+
 # IsaacOrbit-Isaac-Cartpole-v0-PPO
 
-Trained agent model for [NVIDIA Isaac Orbit](https://github.com/NVIDIA-Omniverse/Orbit) environment
+Trained agent for [NVIDIA Isaac Orbit](https://github.com/NVIDIA-Omniverse/Orbit) environments.
 
 - **Task:** Isaac-Cartpole-v0
-- **Agent:** [PPO](https://skrl.readthedocs.io/en/latest/modules/skrl.agents.ppo.html)
+- **Agent:** [PPO](https://skrl.readthedocs.io/en/latest/api/agents/ppo.html)
 
-# Usage (with skrl) 
+# Usage (with skrl)
 
-```python
-from skrl.utils.huggingface import download_model_from_huggingface
+Note: Visit the skrl [Examples](https://skrl.readthedocs.io/en/latest/intro/examples.html) section to access the scripts.
 
-# assuming that there is an agent named `agent`
-path = download_model_from_huggingface("skrl/IsaacOrbit-Isaac-Cartpole-v0-PPO")
-agent.load(path)
-```
+* PyTorch
+
+    ```python
+    from skrl.utils.huggingface import download_model_from_huggingface
+
+    # assuming that there is an agent named `agent`
+    path = download_model_from_huggingface("skrl/IsaacOrbit-Isaac-Cartpole-v0-PPO", filename="agent.pt")
+    agent.load(path)
+    ```
+
+* JAX
+
+    ```python
+    from skrl.utils.huggingface import download_model_from_huggingface
+
+    # assuming that there is an agent named `agent`
+    path = download_model_from_huggingface("skrl/IsaacOrbit-Isaac-Cartpole-v0-PPO", filename="agent.pickle")
+    agent.load(path)
+    ```
 
 # Hyperparameters
 
 ```python
-# https://skrl.readthedocs.io/en/latest/modules/skrl.agents.ppo.html#configuration-and-hyperparameters
-cfg_ppo = PPO_DEFAULT_CONFIG.copy()
-cfg_ppo["rollouts"] = 16  # memory_size
-cfg_ppo["learning_epochs"] = 8
-cfg_ppo["mini_batches"] = 1  # 16 * 512 / 8192
-cfg_ppo["discount_factor"] = 0.99
-cfg_ppo["lambda"] = 0.95
-cfg_ppo["learning_rate"] = 3e-4
-cfg_ppo["learning_rate_scheduler"] = KLAdaptiveRL
-cfg_ppo["learning_rate_scheduler_kwargs"] = {"kl_threshold": 0.008}
-cfg_ppo["random_timesteps"] = 0
-cfg_ppo["learning_starts"] = 0
-cfg_ppo["grad_norm_clip"] = 1.0
-cfg_ppo["ratio_clip"] = 0.2
-cfg_ppo["value_clip"] = 0.2
-cfg_ppo["clip_predicted_values"] = True
-cfg_ppo["entropy_loss_scale"] = 0.0
-cfg_ppo["value_loss_scale"] = 2.0
-cfg_ppo["kl_threshold"] = 0
-cfg_ppo["rewards_shaper"] = None
-cfg_ppo["state_preprocessor"] = RunningStandardScaler
-cfg_ppo["state_preprocessor_kwargs"] = {"size": env.observation_space, "device": device}
-cfg_ppo["value_preprocessor"] = RunningStandardScaler
-cfg_ppo["value_preprocessor_kwargs"] = {"size": 1, "device": device}
-# logging to TensorBoard and writing checkpoints
-cfg_ppo["experiment"]["write_interval"] = 16
-cfg_ppo["experiment"]["checkpoint_interval"] = 80
+# https://skrl.readthedocs.io/en/latest/api/agents/ppo.html#configuration-and-hyperparameters
+cfg = PPO_DEFAULT_CONFIG.copy()
+cfg["rollouts"] = 16  # memory_size
+cfg["learning_epochs"] = 8
+cfg["mini_batches"] = 1  # 16 * 512 / 8192
+cfg["discount_factor"] = 0.99
+cfg["lambda"] = 0.95
+cfg["learning_rate"] = 3e-4
+cfg["learning_rate_scheduler"] = KLAdaptiveRL
+cfg["learning_rate_scheduler_kwargs"] = {"kl_threshold": 0.008}
+cfg["random_timesteps"] = 0
+cfg["learning_starts"] = 0
+cfg["grad_norm_clip"] = 1.0
+cfg["ratio_clip"] = 0.2
+cfg["value_clip"] = 0.2
+cfg["clip_predicted_values"] = True
+cfg["entropy_loss_scale"] = 0.0
+cfg["value_loss_scale"] = 2.0
+cfg["kl_threshold"] = 0
+cfg["rewards_shaper"] = None
+cfg["time_limit_bootstrap"] = True
+cfg["state_preprocessor"] = RunningStandardScaler
+cfg["state_preprocessor_kwargs"] = {"size": env.observation_space, "device": device}
+cfg["value_preprocessor"] = RunningStandardScaler
+cfg["value_preprocessor_kwargs"] = {"size": 1, "device": device}
 ```