README.md

metadata

tags:
  - PandaReachDense
  - PandaReachDense-v3
  - panda-gym
  - deep-rl-course
  - a2c
  - reinforcement-learning
  - stable-baselines3
library_name: stable-baselines3
pipeline_tag: reinforcement-learning
model-index:
  - name: a2c-PandaReachDense
    results:
      - task:
          name: reinforcement-learning
          type: reinforcement-learning
        dataset:
          name: PandaReachDense
          type: PandaReachDense
        metrics:
          - name: mean_reward
            type: mean_reward
            value: '-0.45 +/- 0.12'

A2C Agent playing PandaReachDense

This is a trained model of an A2C agent playing PandaReachDense using stable-baselines3 and panda-gym.

• Mean Reward: -0.45 +/- 0.12
• Result (mean - std): -0.57