README.md

metadata

library_name: stable-baselines3
tags:
  - AntBulletEnv-v0
  - deep-reinforcement-learning
  - reinforcement-learning
  - stable-baselines3
model-index:
  - name: A2C
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: AntBulletEnv-v0
          type: AntBulletEnv-v0
        metrics:
          - type: mean_reward
            value: 1957.59 +/- 114.55
            name: mean_reward
            verified: false

A2C Agent playing AntBulletEnv-v0

This is a trained model of a A2C agent playing AntBulletEnv-v0 using the stable-baselines3 library.

Usage (with Stable-baselines3)

import gym
from stable_baselines3 import A2C
from huggingface_sb3 import load_from_hub

checkpoint = load_from_hub(
    repo_id="AntBulletEnv-v0",
    filename="a2c-AntBulletEnv-v0.zip",
)
model = A2C.load(checkpoint)

# Evaluate the agent and watch it
eval_env = gym.make("AntBulletEnv-v0")
mean_reward, std_reward = evaluate_policy(
    model, eval_env, render=True, n_eval_episodes=5, deterministic=True, warn=False
)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")