Atari Games On Atari 2600 Boxing

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
A3C LSTM hs	37.3	Asynchronous Methods for Deep Reinforcement Learning	-
SARSA	9.8	-	-
MuZero (Res2 Adam)	100	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
GDI-H3	100	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Reactor 500M	99.4	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
A3C FF hs	59.8	Asynchronous Methods for Deep Reinforcement Learning	-
UCT	100	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
ASL DDQN	99.6	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
A2C + SIL	99.6	Self-Imitation Learning	-
Agent57	100	Agent57: Outperforming the Atari Human Benchmark	-
DDQN (tuned) noop	91.6	Dueling Network Architectures for Deep Reinforcement Learning	-
GDI-H3	100	Generalized Data Distribution Iteration	-
CURL	4.8	CURL: Contrastive Unsupervised Representations for Reinforcement Learning	-
DNA	99.9	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
Best Learner	44	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
Ape-X	100	Distributed Prioritized Experience Replay	-
DreamerV2	92	Mastering Atari with Discrete World Models	-
Duel noop	99.4	Dueling Network Architectures for Deep Reinforcement Learning	-
DQN hs	70.3	Deep Reinforcement Learning with Double Q-learning	-
IQN	99.8	Implicit Quantile Networks for Distributional Reinforcement Learning	-

0 of 45 row(s) selected.