Atari Games On Atari 2600 Pong

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
Prior hs	18.9	Prioritized Experience Replay	-
ES FF (1 hour) noop	21.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-
CGP	20	Evolving simple programs for playing Atari games	-
NoisyNet-Dueling	21	Noisy Networks for Exploration	-
Discrete Latent Space World Model (VQ-VAE)	20.2	Smaller World Models for Reinforcement Learning	-
Recurrent Rational DQN Average	18.13	Adaptive Rational Activations to Boost Deep Reinforcement Learning	-
MAC	10.6	Mean Actor Critic	-
DDQN (tuned) noop	20.9	Dueling Network Architectures for Deep Reinforcement Learning	-
DreamerV2	20	Mastering Atari with Discrete World Models	-
C51 noop	20.9	A Distributional Perspective on Reinforcement Learning	-
DNA	19.7	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
DQN Best	21	Playing Atari with Deep Reinforcement Learning	-
Nature DQN	18.9	Human level control through deep reinforcement learning
Gorila	16.7	Massively Parallel Methods for Deep Reinforcement Learning	-
MuZero (Res2 Adam)	20.95	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
CURL	2.1	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	-
DQN noop	19.5	Deep Reinforcement Learning with Double Q-learning	-
Advantage Learning	19.66	Increasing the Action Gap: New Operators for Reinforcement Learning	-
Ape-X	20.9	Distributed Prioritized Experience Replay	-
GDI-I3	21	Generalized Data Distribution Iteration	-

0 of 52 row(s) selected.