README.md

metadata

library_name: skrl
tags:
  - deep-reinforcement-learning
  - reinforcement-learning
  - skrl
model-index:
  - name: PPO
    results:
      - metrics:
          - type: mean_reward
            value: 493.73 +/- 0.58
            name: Total reward (mean)
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: IsaacGymEnvs-Cartpole
          type: IsaacGymEnvs-Cartpole

IsaacGymEnvs-Cartpole-PPO

Trained agent for NVIDIA Isaac Gym Preview environments.

• Task: Cartpole
• Agent: PPO

Usage (with skrl)

Note: Visit the skrl Examples section to access the scripts.

• PyTorch

  from skrl.utils.huggingface import download_model_from_huggingface
  
  # assuming that there is an agent named `agent`
  path = download_model_from_huggingface("skrl/IsaacGymEnvs-Cartpole-PPO", filename="agent.pt")
  agent.load(path)
  

• JAX

  from skrl.utils.huggingface import download_model_from_huggingface
  
  # assuming that there is an agent named `agent`
  path = download_model_from_huggingface("skrl/IsaacGymEnvs-Cartpole-PPO", filename="agent.pickle")
  agent.load(path)
  

Hyperparameters

Note: Undefined parameters keep their values by default.

# 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"] = lambda rewards, timestep, timesteps: rewards * 0.1
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}