HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Name This Game

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
MuZero157177.85Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)101197.71Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D258182.7Recurrent Experience Replay in Distributed Reinforcement Learning
Agent5754386.77Agent57: Outperforming the Atari Human Benchmark
GDI-H336296Generalized Data Distribution Iteration
GDI-I334434Generalized Data Distribution Iteration
GDI-I334434GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
Ape-X25783.3Distributed Prioritized Experience Replay
IQN22682Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-121890Distributional Reinforcement Learning with Quantile Regression
IMPALA (deep)21537.20IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA20226DNA: Proximal Policy Optimization with a Dual Network Architecture
ASL DDQN16535.4Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
DDQN+Pop-Art noop15851.2Learning values across many orders of magnitude
Prior+Duel noop15572.5Dueling Network Architectures for Deep Reinforcement Learning
UCT15410The Arcade Learning Environment: An Evaluation Platform for General Agents
A2C + SIL14958.2Self-Imitation Learning
DreamerV214649Mastering Atari with Discrete World Models
Prior+Duel hs13637.9Deep Reinforcement Learning with Double Q-learning
C51 noop12542.0A Distributional Perspective on Reinforcement Learning
0 of 43 row(s) selected.
Atari Games On Atari 2600 Name This Game | SOTA | HyperAI