edbeeching's picture
edbeeching HF staff
Add `agent.pt` and tag the environment
e9e9aab verified
metadata
library_name: sample-factory
tags:
  - deep-reinforcement-learning
  - reinforcement-learning
  - sample-factory
  - PitfallNoFrameskip-v4
model-index:
  - name: APPO
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: atari_pitfall
          type: atari_pitfall
        metrics:
          - type: mean_reward
            value: '-83.05 +/- 160.20'
            name: mean_reward
            verified: false

A(n) APPO model trained on the atari_pitfall environment. This model was trained using Sample Factory 2.0: https://github.com/alex-petrenko/sample-factory