SPOS

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Playing Games4 results

Atari GamesonAtari 2600 Freeway
Score· 2020-11-30
22
best: 34 (TRPO-hash)
Optimizing the Neural Architecture of Reinforcement Learning Agents arXiv:2011.14632
Atari GamesonAtari 2600 Breakout
Score· 2020-11-30
180.6
best: 864 (GDI-H3(200M frames))
Optimizing the Neural Architecture of Reinforcement Learning Agents arXiv:2011.14632
Video GamesonAtari 2600 Freeway
Score· 2020-11-30
22
best: 34 (TRPO-hash)
Optimizing the Neural Architecture of Reinforcement Learning Agents arXiv:2011.14632
Video GamesonAtari 2600 Breakout
Score· 2020-11-30
180.6
best: 864 (GDI-H3(200M frames))
Optimizing the Neural Architecture of Reinforcement Learning Agents arXiv:2011.14632