Atari Game Playing on Pitfall
114,000ScoreHuman World Record
Evaluation Results
| Method | Links | |
|---|---|---|
| Human World RecordAlgorithm Category=Human2019.01 | 114,000 | |
| Go-ExploreAlgorithm Category=Reinforcement Learning, Domain knowledge utilization=true, Score Aggregation=Best2019.01 | 107,363 | |
| TDC+CMCAlgorithm Category=Imitation Learning2019.01 | 76,813 | |
| Go-ExploreAlgorithm Category=Reinforcement Learning, Domain knowledge utilization=true, Score Aggregation=Average2019.01 | 59,494 | |
| Human ExpertAlgorithm Category=Human2019.01 | 47,821 | |
| Average HumanAlgorithm Category=Human2019.01 | 6,464 | |
| Ape-X DQfDAlgorithm Category=Imitation Learning2019.01 | 3,997 | |
| DQfDAlgorithm Category=Imitation Learning2019.01 | 57 | |
| Duel. DQNAlgorithm Category=Reinforcement Learning2019.01 | 0 | |
| DQN-CTSAlgorithm Category=Reinforcement Learning2019.01 | 0 | |
| DQN-PixelCNNAlgorithm Category=Reinforcement Learning2019.01 | 0 | |
| C51Algorithm Category=Reinforcement Learning2019.01 | 0 | |
| UBEAlgorithm Category=Reinforcement Learning2019.01 | 0 | |
| RainbowAlgorithm Category=Reinforcement Learning2019.01 | 0 | |
| Ape-XAlgorithm Category=Reinforcement Learning2019.01 | -1 | |
| IMPALAAlgorithm Category=Reinforcement Learning2019.01 | -1.2 | |
| Pop-ArtAlgorithm Category=Reinforcement Learning2019.01 | -3 | |
| RNDAlgorithm Category=Reinforcement Learning2019.01 | -3 | |
| ReactorAlgorithm Category=Reinforcement Learning2019.01 | -3.5 | |
| Prior. DQNAlgorithm Category=Reinforcement Learning2019.01 | -15 | |
| DDQNAlgorithm Category=Reinforcement Learning2019.01 | -30 | |
| A3CAlgorithm Category=Reinforcement Learning2019.01 | -78 | |
| DeepCSAlgorithm Category=Reinforcement Learning2019.01 | -186 | |
| A3C-CTSAlgorithm Category=Reinforcement Learning2019.01 | -259 | |
| DQNAlgorithm Category=Reinforcement Learning2019.01 | -286.1 |