Atari Games On Atari 2600 James Bond

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
Duel noop	1312.5	Dueling Network Architectures for Deep Reinforcement Learning
Prior hs	3961.0	Prioritized Experience Replay
Rational DQN Average	1122	Adaptive Rational Activations to Boost Deep Reinforcement Learning
R2D2	25354.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DreamerV2	40445	Mastering Atari with Discrete World Models
Recurrent Rational DQN Average	1137	Adaptive Rational Activations to Boost Deep Reinforcement Learning
CGP	6130	Evolving simple programs for playing Atari games
Duel hs	835.5	Dueling Network Architectures for Deep Reinforcement Learning
Prior noop	5148.0	Prioritized Experience Replay
Best Learner	202.8	The Arcade Learning Environment: An Evaluation Platform for General Agents
GDI-I3	594500	Generalized Data Distribution Iteration	-
A2C + SIL	310.8	Self-Imitation Learning
Ape-X	21322.5	Distributed Prioritized Experience Replay
IQN	35108	Implicit Quantile Networks for Distributional Reinforcement Learning
DNA	14102	DNA: Proximal Policy Optimization with a Dual Network Architecture
Agent57	135784.96	Agent57: Outperforming the Atari Human Benchmark
Prior+Duel noop	812.0	Dueling Network Architectures for Deep Reinforcement Learning
IMPALA (deep)	601.50	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
SAC	68.3	Soft Actor-Critic for Discrete Action Settings
GDI-I3	594500	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-

0 of 45 row(s) selected.