| Agent57: Outperforming the Atari Human Benchmark | ✓ Link | 44199.93 | Agent57 | 2020-03-30 |
| First return, then explore | ✓ Link | 19671 | Go-Explore | 2020-04-27 |
| Self-supervised network distillation: an effective approach to exploration in sparse reward environments | ✓ Link | 12460 | SND-STD | 2023-02-22 |
| Self-supervised network distillation: an effective approach to exploration in sparse reward environments | ✓ Link | 11865 | SND-VIC | 2023-02-22 |
| Self-supervised network distillation: an effective approach to exploration in sparse reward environments | ✓ Link | 11582 | SND-V | 2023-02-22 |
| GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning | | 11074 | GDI-I3 | 2021-06-11 |
| Generalized Data Distribution Iteration | | 11074 | GDI-I3 | 2022-06-07 |
| Generalized Data Distribution Iteration | | 9105 | GDI-H3 | 2022-06-07 |
| Evolving simple programs for playing Atari games | ✓ Link | 8324 | CGP | 2018-06-14 |
| Implicit Quantile Networks for Distributional Reinforcement Learning | ✓ Link | 8007 | IQN | 2018-06-14 |
| Distributional Reinforcement Learning with Quantile Regression | ✓ Link | 6740 | QR-DQN-1 | 2017-10-27 |
| Noisy Networks for Exploration | ✓ Link | 6522 | NoisyNet-Dueling | 2017-06-30 |
| Online and Offline Reinforcement Learning by Planning with a Learned Model | ✓ Link | 5132.95 | MuZero (Res2 Adam) | 2021-04-13 |
| Increasing the Action Gap: New Operators for Reinforcement Learning | ✓ Link | 4785.16 | Advantage Learning | 2015-12-15 |
| Recurrent Experience Replay in Distributed Reinforcement Learning | ✓ Link | 3787.2 | R2D2 | 2019-05-01 |
| Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity | ✓ Link | 3506.8 | ASL DDQN | 2023-05-07 |
| Exploration by Random Network Distillation | ✓ Link | 3282 | RND | 2018-10-30 |
| Distributed Prioritized Experience Replay | ✓ Link | 2892.9 | Ape-X | 2018-03-02 |
| IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures | ✓ Link | 2365.00 | IMPALA (deep) | 2018-02-05 |
| Count-Based Exploration with the Successor Representation | ✓ Link | 2244.6 | DQNMMCe | 2018-07-31 |
| DNA: Proximal Policy Optimization with a Dual Network Architecture | ✓ Link | 2225 | DNA | 2022-06-20 |
| Mastering Atari with Discrete World Models | ✓ Link | 922 | DreamerV2 | 2020-10-05 |
| Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model | ✓ Link | 56.62 | MuZero | 2019-11-19 |