HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Assault

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
MuZero143972.03Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2108197.0Recurrent Experience Replay in Distributed Reinforcement Learning
GDI-H397155Generalized Data Distribution Iteration
Agent5767212.67Agent57: Outperforming the Atari Human Benchmark
GDI-I363876Generalized Data Distribution Iteration
MuZero (Res2 Adam)33292.22Online and Offline Reinforcement Learning by Planning with a Learned Model
IQN29091Implicit Quantile Networks for Distributional Reinforcement Learning
Ape-X24559.4Distributed Prioritized Experience Replay
DreamerV223625Mastering Atari with Discrete World Models
QR-DQN-122012Distributional Reinforcement Learning with Quantile Regression
IMPALA (deep)19148.47IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA16293DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C LSTM hs14497.9Asynchronous Methods for Deep Reinforcement Learning
ASL DDQN14372.8Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel noop11477.0Dueling Network Architectures for Deep Reinforcement Learning
NoisyNet-Dueling11231Noisy Networks for Exploration
Prior+Duel hs10950.6Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs10950.6Deep Reinforcement Learning with Double Q-learning
DDQN+Pop-Art noop9011.6Learning values across many orders of magnitude
Reactor 500M8323.3The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
0 of 45 row(s) selected.
Atari Games On Atari 2600 Assault | SOTA | HyperAI