Deep RL Agents
Collection
A collection of models trained using deep RL for a variety of games.
•
11 items
•
Updated
•
1
PPO Agent playing HumanoidStandup-v2
This is a trained model of a PPO agent playing HumanoidStandup-v2 using the stable-baselines3 library.
- Downloads last month
- 0
Collection including MattBoraske/ppo-HumanoidStandup-v2-init
Evaluation results
- mean_reward on HumanoidStandup-v2self-reported65822.31 +/- 10972.33