edbeeching/atari_2B_atari_solaris_1111

1---2library_name: sample-factory3tags:4- deep-reinforcement-learning5- reinforcement-learning6- sample-factory7- SolarisNoFrameskip-v48model-index:9- name: APPO10  results:11  - task:12      type: reinforcement-learning13      name: reinforcement-learning14    dataset:15      name: atari_solaris16      type: atari_solaris17    metrics:18    - type: mean_reward19      value: 3494.00 +/- 2422.1920      name: mean_reward21      verified: false22---23 24A(n) **APPO** model trained on the **atari_solaris** environment.25This model was trained using Sample Factory 2.0: https://github.com/alex-petrenko/sample-factory26