Atari Games On Atari 2600 Skiing

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
Full Tree	0	The Arcade Learning Environment: An Evaluation Platform for General Agents
Best Learner	0	The Arcade Learning Environment: An Evaluation Platform for General Agents
Go-Explore	-3660	First return, then explore
Agent57	-4202.6	Agent57: Outperforming the Atari Human Benchmark
GDI-H3	-6025	Generalized Data Distribution Iteration
GDI-I3	-6774	Generalized Data Distribution Iteration
GDI-I3	-6774	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
NoisyNet-Dueling	-7550	Noisy Networks for Exploration
ASL DDQN	-8295.4	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
CGP	-9011	Evolving simple programs for playing Atari games
FQF	-9085.3	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
IQN	-9289	Implicit Quantile Networks for Distributional Reinforcement Learning
DreamerV2	-9299	Mastering Atari with Discrete World Models
QR-DQN-1	-9324	Distributional Reinforcement Learning with Quantile Regression
IMPALA (deep)	-10180.38	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Ape-X	-10789.9	Distributed Prioritized Experience Replay
Advantage Learning	-13264.51	Increasing the Action Gap: New Operators for Reinforcement Learning
Rational DQN Average	-23487	Adaptive Rational Activations to Boost Deep Reinforcement Learning
Recurrent Rational DQN Average	-23582	Adaptive Rational Activations to Boost Deep Reinforcement Learning
MuZero	-29968.36	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

0 of 23 row(s) selected.

Command Palette

Atari Games On Atari 2600 Skiing

평가 지표

평가 결과