HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Atari Games On Atari 2600 Solaris

Metrics

Score

Results

Performance results of various models on this benchmark

Paper Title
Agent5744199.93Agent57: Outperforming the Atari Human Benchmark
Go-Explore19671First return, then explore
SND-STD12460Self-supervised network distillation: an effective approach to exploration in sparse reward environments
SND-VIC11865Self-supervised network distillation: an effective approach to exploration in sparse reward environments
SND-V11582Self-supervised network distillation: an effective approach to exploration in sparse reward environments
GDI-I311074Generalized Data Distribution Iteration
GDI-I311074GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
GDI-H39105Generalized Data Distribution Iteration
CGP8324Evolving simple programs for playing Atari games
IQN8007Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-16740Distributional Reinforcement Learning with Quantile Regression
NoisyNet-Dueling6522Noisy Networks for Exploration
MuZero (Res2 Adam)5132.95Online and Offline Reinforcement Learning by Planning with a Learned Model
Advantage Learning4785.16Increasing the Action Gap: New Operators for Reinforcement Learning
R2D23787.2Recurrent Experience Replay in Distributed Reinforcement Learning
ASL DDQN3506.8Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
RND3282Exploration by Random Network Distillation
Ape-X2892.9Distributed Prioritized Experience Replay
IMPALA (deep)2365.00IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DQNMMCe2244.6Count-Based Exploration with the Successor Representation
0 of 23 row(s) selected.
Atari Games On Atari 2600 Solaris | SOTA | HyperAI