HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Atlantis

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
GDI-H33837300Generalized Data Distribution Iteration
GDI-I33803000Generalized Data Distribution Iteration
A2C + SIL3084781.7Self-Imitation Learning
POP3D2193605.67Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
MuZero1674767.20Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D21620764.0Recurrent Experience Replay in Distributed Reinforcement Learning
Agent571528841.76Agent57: Outperforming the Atari Human Benchmark
Persistent AL1465250Increasing the Action Gap: New Operators for Reinforcement Learning
ES FF (1 hour) noop1267410.0Evolution Strategies as a Scalable Alternative to Reinforcement Learning
MuZero (Res2 Adam)1137475.12Online and Offline Reinforcement Learning by Planning with a Learned Model
Bootstrapped DQN994500Deep Exploration via Bootstrapped DQN
DreamerV2978778Mastering Atari with Discrete World Models
IQN978200Implicit Quantile Networks for Distributional Reinforcement Learning
NoisyNet-Dueling972175Noisy Networks for Exploration
QR-DQN-1971850Distributional Reinforcement Learning with Quantile Regression
ASL DDQN947275Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Ape-X944497.5Distributed Prioritized Experience Replay
DNA932559DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C FF hs911091.0Asynchronous Methods for Deep Reinforcement Learning
A3C LSTM hs875822.0Asynchronous Methods for Deep Reinforcement Learning
0 of 42 row(s) selected.
Atari Games On Atari 2600 Atlantis | SOTA | HyperAI