Atari Games On Atari 2600 Frostbite

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
DDQN+Pop-Art noop	3469.6	Learning values across many orders of magnitude	-
A3C LSTM hs	197.6	Asynchronous Methods for Deep Reinforcement Learning	-
Persistent AL	3248.96	Increasing the Action Gap: New Operators for Reinforcement Learning	-
DNA	320	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
Duel hs	2332.4	Dueling Network Architectures for Deep Reinforcement Learning	-
DQN noop	797.4	Deep Reinforcement Learning with Double Q-learning	-
Prior+Duel noop	7413.0	Dueling Network Architectures for Deep Reinforcement Learning	-
MP-EB	507.0	Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models	-
R2D2	315456.4	Recurrent Experience Replay in Distributed Reinforcement Learning	-
ES FF (1 hour) noop	370.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-
Best Learner	216.9	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
Prior+Duel hs	4038.4	Deep Reinforcement Learning with Double Q-learning	-
TRPO-hash	5214.0	#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning	-
MuZero	631378.53	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	-
Prior hs	3510.0	Prioritized Experience Replay	-
Bootstrapped DQN	2181.4	Deep Exploration via Bootstrapped DQN	-
CURL	924	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	-
Prior noop	4380.1	Prioritized Experience Replay	-
A3C FF hs	190.5	Asynchronous Methods for Deep Reinforcement Learning	-
VPN	3811	Value Prediction Network	-

0 of 53 row(s) selected.