metadata
library_name: stable-baselines3
tags:
- BipedalWalker-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: TD3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: BipedalWalker-v3
type: BipedalWalker-v3
metrics:
- type: mean_reward
value: 50.22 +/- 91.71
name: mean_reward
verified: false
TD3 Agent playing BipedalWalker-v3
This is a trained model of a TD3 agent playing BipedalWalker-v3 using the stable-baselines3 library.
Usage (with Stable-baselines3)
TODO: Add your code
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
Dude is getting there but needs hyperparameter tuning. Will try SAC next as the tuning is a known entity so will be quicker.