chirbard/ppo-BipedalWalker-v3

PPO Agent playing BipedalWalker-v3

This is a trained model of a PPO agent playing BipedalWalker-v3 using the stable-baselines3 library.

Hyperparameters

model = PPO(
    policy = 'MlpPolicy',
    env = env,
    n_steps = 1024,
    batch_size = 64,
    n_epochs = 4,
    gamma = 0.99,
    gae_lambda = 0.98,
    ent_coef = 0.01,
    verbose=1)

Train Time

Trained for 3 000 000 timesteps. Training took 1 hour and 8 minutes on Nvidia RTX A2000 Laptop.