Atari Games On Atari 2600 Freeway

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
A3C FF (1 day) hs	0.1	Asynchronous Methods for Deep Reinforcement Learning	-
Bootstrapped DQN	33.9	Deep Exploration via Bootstrapped DQN	-
SAC	4.4	Soft Actor-Critic for Discrete Action Settings	-
Duel noop	0.0	Dueling Network Architectures for Deep Reinforcement Learning	-
Duel hs	0.2	Dueling Network Architectures for Deep Reinforcement Learning	-
A3C FF hs	0.1	Asynchronous Methods for Deep Reinforcement Learning	-
Intrinsic Reward Agent	32.8	Large-Scale Study of Curiosity-Driven Learning	-
POP3D	21.21	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-
Gorila	10.2	Massively Parallel Methods for Deep Reinforcement Learning	-
Discrete Latent Space World Model (VQ-VAE)	29	Smaller World Models for Reinforcement Learning	-
Go-Explore	34	First return, then explore	-
Prior hs	28.9	Prioritized Experience Replay	-
DQN-PixelCNN	31.7	Count-Based Exploration with Neural Density Models	-
Ape-X	33.7	Distributed Prioritized Experience Replay	-
DDQN+Pop-Art noop	33.4	Learning values across many orders of magnitude	-
Sarsa-φ-EB	0.0	Count-Based Exploration in Feature Space for Reinforcement Learning	-
ES FF (1 hour) noop	31.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-
Advantage Learning	31.72	Increasing the Action Gap: New Operators for Reinforcement Learning	-
R2D2	32.5	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Best Baseline	22.5	The Arcade Learning Environment: An Evaluation Platform for General Agents	-

0 of 59 row(s) selected.