swaroop06
/

a2c-PandaPushDense-v2

Reinforcement Learning

stable-baselines3

PandaPushDense-v2

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

A2C agent playing PandaPushDense-v2

This is a trained model of an A2C agent playing PandaPushDense-v2 for the Hugging Face Deep Reinforcement Learning Course (Unit 6 (PandaPush)).

Evaluation Results

Mean Reward: -0.50 +/- 0.20
Environment: PandaPushDense-v2
Algorithm: A2C
Library: stable-baselines3

Usage

Trained and evaluated for the Hugging Face Deep RL Course.

Downloads last month: 4

Video Preview

Reinforcement Learning

loading

Evaluation results

mean_reward on PandaPushDense-v2
self-reported

-0.50 +/- 0.20