HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Kung Fu Master

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
GDI-H31666665Generalized Data Distribution Iteration
GDI-H3 (200M)1666000GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning
R2D2233413.3Recurrent Experience Replay in Distributed Reinforcement Learning
Agent57206845.82Agent57: Outperforming the Atari Human Benchmark
MuZero204824.00Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3140440Generalized Data Distribution Iteration
MuZero (Res2 Adam)116726.96Online and Offline Reinforcement Learning by Planning with a Learned Model
FQF111138.5Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DNA110962DNA: Proximal Policy Optimization with a Dual Network Architecture
Ape-X97829.5Distributed Prioritized Experience Replay
ASL DDQN85182Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
QR-DQN-176642Distributional Reinforcement Learning with Quantile Regression
IQN73512Implicit Quantile Networks for Distributional Reinforcement Learning
DreamerV262741Mastering Atari with Discrete World Models
CGP57400Evolving simple programs for playing Atari games
UCT48854.5The Arcade Learning Environment: An Evaluation Platform for General Agents
Prior+Duel noop48375.0Dueling Network Architectures for Deep Reinforcement Learning
C51 noop48192.0A Distributional Perspective on Reinforcement Learning
IMPALA (deep)43375.50IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
NoisyNet-Dueling41672Noisy Networks for Exploration
0 of 43 row(s) selected.
Atari Games On Atari 2600 Kung Fu Master | SOTA | HyperAI