HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Bank Heist

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
MuZero (Res2 Adam)27219.8Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D224235.9Recurrent Experience Replay in Distributed Reinforcement Learning
Agent5723071.5Agent57: Outperforming the Atari Human Benchmark
Ape-X1716.4Distributed Prioritized Experience Replay
Duel noop1611.9Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop1503.1Dueling Network Architectures for Deep Reinforcement Learning
IQN1416Implicit Quantile Networks for Distributional Reinforcement Learning
GDI-I31401Generalized Data Distribution Iteration
GDI-H31380Generalized Data Distribution Iteration
ASL DDQN1340.9Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
NoisyNet-Dueling1318Noisy Networks for Exploration
DNA1286DNA: Proximal Policy Optimization with a Dual Network Architecture
MuZero1278.98Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Reactor 500M1259.7The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
QR-DQN-11249Distributional Reinforcement Learning with Quantile Regression
IMPALA (deep)1223.15IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
POP3D1212.23Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Bootstrapped DQN1208Deep Exploration via Bootstrapped DQN
A2C + SIL1137.8Self-Imitation Learning
Duel hs1129.3Dueling Network Architectures for Deep Reinforcement Learning
0 of 45 row(s) selected.
Atari Games On Atari 2600 Bank Heist | SOTA | HyperAI