HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Atari Games On Atari 2600 Hero

Metrics

Score

Results

Performance results of various models on this benchmark

Paper Title
Agent57114736.26Agent57: Outperforming the Atari Human Benchmark
MuZero49244.11Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D239537.1Recurrent Experience Replay in Distributed Reinforcement Learning
C51 noop38874A Distributional Perspective on Reinforcement Learning
GDI-I338330Generalized Data Distribution Iteration
GDI-I338330GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
GDI-H338225Generalized Data Distribution Iteration
MuZero (Res2 Adam)37234.31Online and Offline Reinforcement Learning by Planning with a Learned Model
IMPALA (deep)33730.55IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
A2C + SIL33156.7Self-Imitation Learning
A3C FF hs32464.1Asynchronous Methods for Deep Reinforcement Learning
Ape-X31655.9Distributed Prioritized Experience Replay
NoisyNet-Dueling31533Noisy Networks for Exploration
FQF30926.2Fully Parameterized Quantile Function for Distributional Reinforcement Learning
A3C LSTM hs28889.5Asynchronous Methods for Deep Reinforcement Learning
A3C FF (1 day) hs28765.8Asynchronous Methods for Deep Reinforcement Learning
IQN28386Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN26578.5Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
DNA24904DNA: Proximal Policy Optimization with a Dual Network Architecture
Advantage Learning24788.86Increasing the Action Gap: New Operators for Reinforcement Learning
0 of 44 row(s) selected.
Atari Games On Atari 2600 Hero | SOTA | HyperAI