SOTAVerified

Atari Games

The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.

( Image credit: Playing Atari with Deep Reinforcement Learning )

Papers

Showing 451460 of 625 papers

TitleStatusHype
Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement LearningCode0
Improved robustness of reinforcement learning policies upon conversion to spiking neuronal network platforms applied to ATARI gamesCode0
DQN with model-based exploration: efficient learning on environments with sparse rewards0
Towards automatic construction of multi-network models for heterogeneous multi-task learning0
Deep Reinforcement Learning with Decorrelation0
Reinforcement Learning with Dynamic Boltzmann Softmax UpdatesCode0
Hybrid Reinforcement Learning with Expert State SequencesCode0
Learning Self-Game-Play Agents for Combinatorial Optimization Problems0
MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning ExperimentsCode0
Continual Learning Using World Models for Pseudo-Rehearsal0
Show:102550
← PrevPage 46 of 63Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GDI-I3(200M frames)Score864Unverified
2GDI-H3(200M frames)Score864Unverified
3GDI-H3Score864Unverified
4GDI-I3Score864Unverified
5Bootstrapped DQNScore855Unverified
6FQFScore854.2Unverified
7R2D2Score837.7Unverified
8Ape-XScore800.9Unverified
9Agent57Score790.4Unverified
10IMPALA (deep)Score787.34Unverified
#ModelMetricClaimedVerifiedStatus
1IQNScore34Unverified
2QR-DQN-1Score34Unverified
3TRPO-hashScore34Unverified
4NoisyNet-DuelingScore34Unverified
5GDI-H3Score34Unverified
6GDI-H3(200M frames)Score34Unverified
7GDI-I3Score34Unverified
8Go-ExploreScore34Unverified
9Bootstrapped DQNScore33.9Unverified
10C51 noopScore33.9Unverified
#ModelMetricClaimedVerifiedStatus
1Agent57Score580,328.14Unverified
2QR-DQN-1Score572,510Unverified
3R2D2Score408,850Unverified
4IMPALA (deep)Score351,200.12Unverified
5Ape-XScore302,391.3Unverified
6A2C + SILScore104,975.6Unverified
7MuZero (Res2 Adam)Score94,906.25Unverified
8DreamerV2Score94,688Unverified
9MuZeroScore72,276Unverified
10DNAScore52,398Unverified
#ModelMetricClaimedVerifiedStatus
1GDI-H3Score1,000,000Unverified
2GDI-H3(200M frames)Score1,000,000Unverified
3Agent57Score999,997.63Unverified
4R2D2Score999,996.7Unverified
5MuZeroScore999,976.52Unverified
6MuZero (Res2 Adam)Score999,659.18Unverified
7GDI-I3Score943,910Unverified
8Ape-XScore392,952.3Unverified
9C51 noopScore266,434Unverified
10Duel noopScore50,254.2Unverified