Atari Games On Atari 2600 Kung Fu Master

評価指標

Score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Score	Paper Title	Repository
Prior noop	39581.0	Prioritized Experience Replay
DQN hs	20882.0	Deep Reinforcement Learning with Double Q-learning
DDQN (tuned) noop	29710.0	Dueling Network Architectures for Deep Reinforcement Learning
A3C LSTM hs	40835.0	Asynchronous Methods for Deep Reinforcement Learning
Advantage Learning	32182.99	Increasing the Action Gap: New Operators for Reinforcement Learning
Prior+Duel noop	48375.0	Dueling Network Architectures for Deep Reinforcement Learning
A3C FF (1 day) hs	3046.0	Asynchronous Methods for Deep Reinforcement Learning
GDI-I3	140440	Generalized Data Distribution Iteration	-
FQF	111138.5	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DDQN (tuned) hs	30207.0	Deep Reinforcement Learning with Double Q-learning
Bootstrapped DQN	36733.3	Deep Exploration via Bootstrapped DQN
DDQN+Pop-Art noop	34393.0	Learning values across many orders of magnitude	-
CGP	57400	Evolving simple programs for playing Atari games
POP3D	33728	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Persistent AL	34650.91	Increasing the Action Gap: New Operators for Reinforcement Learning
GDI-H3 (200M)	1666000	GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning	-
DreamerV2	62741	Mastering Atari with Discrete World Models
NoisyNet-Dueling	41672	Noisy Networks for Exploration
Gorila	20620.0	Massively Parallel Methods for Deep Reinforcement Learning
DQN noop	26059.0	Deep Reinforcement Learning with Double Q-learning

0 of 43 row(s) selected.