Atari Games On Atari 2600 Tennis

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
SARSA	0.0	-	-
Duel noop	5.1	Dueling Network Architectures for Deep Reinforcement Learning
ASL DDQN	22.3	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
Recurrent Rational DQN Average	20.6	Adaptive Rational Activations to Boost Deep Reinforcement Learning
POP3D	-8.32	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
R2D2	-0.1	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Rational DQN Average	20.5	Adaptive Rational Activations to Boost Deep Reinforcement Learning
GDI-I3	24	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Nature DQN	-2.5	Human level control through deep reinforcement learning
Agent57	23.84	Agent57: Outperforming the Atari Human Benchmark
DQN noop	12.2	Deep Reinforcement Learning with Double Q-learning
IQN	23.6	Implicit Quantile Networks for Distributional Reinforcement Learning
UCT	2.8	The Arcade Learning Environment: An Evaluation Platform for General Agents
Gorila	-0.7	Massively Parallel Methods for Deep Reinforcement Learning
A3C LSTM hs	-6.4	Asynchronous Methods for Deep Reinforcement Learning
Prior hs	-5.3	Prioritized Experience Replay
MuZero	0.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
ES FF (1 hour) noop	-4.5	Evolution Strategies as a Scalable Alternative to Reinforcement Learning
QR-DQN-1	23.6	Distributional Reinforcement Learning with Quantile Regression
DQN hs	11.1	Deep Reinforcement Learning with Double Q-learning

0 of 43 row(s) selected.