poca-SoccerTwos

This is a trained model of a POCA agent playing ML-Agents-SoccerTwos. This model was trained as part of the Hugging Face Deep Reinforcement Learning Course.

Evaluation Results

• Environment: ML-Agents-SoccerTwos
• Algorithm: POCA
• Library: ml-agents
• Mean Reward: 0.50 +/- 0.05

Usage

To evaluate this model locally or play with it, download the model files from this repository.