HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Atari Games On Atari 2600 Boxing

Metrics

Score

Results

Performance results of various models on this benchmark

Paper Title
MuZero (Res2 Adam)100Online and Offline Reinforcement Learning by Planning with a Learned Model
GDI-H3100GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
UCT100The Arcade Learning Environment: An Evaluation Platform for General Agents
Agent57100Agent57: Outperforming the Atari Human Benchmark
GDI-H3100Generalized Data Distribution Iteration
Ape-X100Distributed Prioritized Experience Replay
NoisyNet-Dueling100Noisy Networks for Exploration
MuZero100.00Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3100Generalized Data Distribution Iteration
IMPALA (deep)99.96IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA99.9DNA: Proximal Policy Optimization with a Dual Network Architecture
QR-DQN-199.9Distributional Reinforcement Learning with Quantile Regression
IQN99.8Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN99.6Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
A2C + SIL99.6Self-Imitation Learning
Reactor 500M99.4The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
Duel noop99.4Dueling Network Architectures for Deep Reinforcement Learning
DDQN+Pop-Art noop99.3Learning values across many orders of magnitude
Prior+Duel noop98.9Dueling Network Architectures for Deep Reinforcement Learning
R2D298.5Recurrent Experience Replay in Distributed Reinforcement Learning
0 of 45 row(s) selected.