Atari Games On Atari 2600 Asterix

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
Ape-X	313305	Distributed Prioritized Experience Replay
SARSA	1332	-	-
ES FF (1 hour) noop	1440	Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Prior hs	22484.5	Prioritized Experience Replay
Prior+Duel hs	364200.0	Dueling Network Architectures for Deep Reinforcement Learning
CGP	1880	Evolving simple programs for playing Atari games
DDQN (tuned) hs	16837.0	Deep Reinforcement Learning with Double Q-learning
NoisyNet-Dueling	28350	Noisy Networks for Exploration
SAC	272	Soft Actor-Critic for Discrete Action Settings
DNA	323965	DNA: Proximal Policy Optimization with a Dual Network Architecture
R2D2	999153.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
ASL DDQN	567640	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
Best Learner	987.3	The Arcade Learning Environment: An Evaluation Platform for General Agents
DDQN+Pop-Art noop	18919.5	Learning values across many orders of magnitude	-
IMPALA (deep)	300732.00	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Nature DQN	6012	Human level control through deep reinforcement learning
A3C FF hs	22140.5	Asynchronous Methods for Deep Reinforcement Learning
GDI-H3	999999	Generalized Data Distribution Iteration	-
DDQN (tuned) noop	17356.5	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	375080.0	Dueling Network Architectures for Deep Reinforcement Learning

0 of 49 row(s) selected.