HyperAIHyperAI

Command Palette

Search for a command to run...

Atari Games On Atari 2600 Time Pilot

Metrics

Score

Results

Performance results of various models on this benchmark

Paper TitleRepository
MuZero476763.90Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-H3450810Generalized Data Distribution Iteration-
R2D2445377.3Recurrent Experience Replay in Distributed Reinforcement Learning-
MuZero (Res2 Adam)424011.16Online and Offline Reinforcement Learning by Planning with a Learned Model
Agent57405425.31Agent57: Outperforming the Atari Human Benchmark
GDI-I3216770Generalized Data Distribution Iteration-
GDI-I3216770GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
Ape-X87085Distributed Prioritized Experience Replay
UCT63854.5The Arcade Learning Environment: An Evaluation Platform for General Agents
IMPALA (deep)48481.50IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DreamerV237945Mastering Atari with Discrete World Models
A3C LSTM hs27202.0Asynchronous Methods for Deep Reinforcement Learning
Rational DQN Average17632Adaptive Rational Activations to Boost Deep Reinforcement Learning
NoisyNet-Dueling17301Noisy Networks for Exploration
Recurrent Rational DQN Average13261Adaptive Rational Activations to Boost Deep Reinforcement Learning
DNA12774DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C FF hs12679.0Asynchronous Methods for Deep Reinforcement Learning
IQN12236Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN12071Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
CGP12040Evolving simple programs for playing Atari games
0 of 44 row(s) selected.
Atari Games On Atari 2600 Time Pilot | SOTA | HyperAI