Atari Games On Atari 2600 Double Dunk

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
QR-DQN-1	21.9	Distributional Reinforcement Learning with Quantile Regression	-
MuZero	23.94	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	-
A2C + SIL	21.5	Self-Imitation Learning	-
Duel noop	0.1	Dueling Network Architectures for Deep Reinforcement Learning	-
Gorila	-11.3	Massively Parallel Methods for Deep Reinforcement Learning	-
IQN	5.6	Implicit Quantile Networks for Distributional Reinforcement Learning	-
Prior+Duel noop	-12.5	Dueling Network Architectures for Deep Reinforcement Learning	-
DDQN (tuned) hs	-0.3	Deep Reinforcement Learning with Double Q-learning	-
IMPALA (deep)	-0.33	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	-
GDI-I3	24	Generalized Data Distribution Iteration	-
Prior noop	18.5	Prioritized Experience Replay	-
DreamerV2	17	Mastering Atari with Discrete World Models	-
Prior+Duel hs	-10.7	Deep Reinforcement Learning with Double Q-learning	-
DQN noop	-6.6	Deep Reinforcement Learning with Double Q-learning	-
UCT	24	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
DDQN+Pop-Art noop	-11.5	Learning values across many orders of magnitude	-
A3C FF (1 day) hs	0.1	Asynchronous Methods for Deep Reinforcement Learning	-
Nature DQN	-18.1	Human level control through deep reinforcement learning
SARSA	-16.0	-	-
DDQN (tuned) noop	-5.5	Dueling Network Architectures for Deep Reinforcement Learning	-

0 of 43 row(s) selected.