Atari Games On Atari 2600 Alien

Score

评测结果

各个模型在此基准测试上的表现结果

模型名称	Score	Paper Title	Repository
DNA	5021	DNA: Proximal Policy Optimization with a Dual Network Architecture
Persistent AL	5699.81	Increasing the Action Gap: New Operators for Reinforcement Learning
Prior+Duel noop	3941.0	Dueling Network Architectures for Deep Reinforcement Learning
A2C + SIL	2242.2	Self-Imitation Learning
A3C LSTM hs	945.3	Asynchronous Methods for Deep Reinforcement Learning
GDI-H3	48735	Generalized Data Distribution Iteration	-
CGP	1978	Evolving simple programs for playing Atari games
Best Learner	939.2	The Arcade Learning Environment: An Evaluation Platform for General Agents
MuZero	741812.63	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2	229496.9	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Gorila	813.5	Massively Parallel Methods for Deep Reinforcement Learning
DDQN (tuned) hs	1033.4	Deep Reinforcement Learning with Double Q-learning
A3C FF hs	518.4	Asynchronous Methods for Deep Reinforcement Learning
Prior noop	4203.8	Prioritized Experience Replay
SAC	216.9	Soft Actor-Critic for Discrete Action Settings
Duel noop	4461.4	Dueling Network Architectures for Deep Reinforcement Learning
DDQN (tuned) noop	3747.7	Dueling Network Architectures for Deep Reinforcement Learning
Reactor 500M	12689.1	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
GDI-H3(1B frames)	279700	GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning	-
Bootstrapped DQN	2436.6	Deep Exploration via Bootstrapped DQN

0 of 49 row(s) selected.