HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Battle Zone

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
Agent57934134.88Agent57: Outperforming the Atari Human Benchmark
MuZero848623.00Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-H3824360Generalized Data Distribution Iteration
R2D2751880.0Recurrent Experience Replay in Distributed Reinforcement Learning
GDI-I3478830Generalized Data Distribution Iteration
MuZero (Res2 Adam)178716.9Online and Offline Reinforcement Learning by Planning with a Learned Model
Ape-X98895Distributed Prioritized Experience Replay
FQF87928.6Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DNA71003DNA: Proximal Policy Optimization with a Dual Network Architecture
UCT70333.3The Arcade Learning Environment: An Evaluation Platform for General Agents
Reactor 500M64070.0The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
NoisyNet-Dueling52262Noisy Networks for Exploration
IQN42244Implicit Quantile Networks for Distributional Reinforcement Learning
DreamerV240325Mastering Atari with Discrete World Models
QR-DQN-139268Distributional Reinforcement Learning with Quantile Regression
ASL DDQN38986Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Bootstrapped DQN38666.7Deep Exploration via Bootstrapped DQN
Duel noop37150.0Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop35520.0Dueling Network Architectures for Deep Reinforcement Learning
Persistent AL34583.07Increasing the Action Gap: New Operators for Reinforcement Learning
0 of 47 row(s) selected.