Research map / Reinforcement learning / Visual and representation RL
MADE: Exploration via Maximizing Deviation from Explored Regions
Tianjun Zhang, Paria Rashidinejad, Jiantao Jiao, Yuandong Tian, Joseph E. Gonzalez, Stuart Russell
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add MADE intrinsic reward to IMPALA | IMPALA · MiniGrid procedurally generated tasks | samples to maximum reward: 2-5 times fewer samples | Improved |
| Add MADE intrinsic reward to RAD | RAD · DeepMind Control Suite tasks | sample efficiency: 2.6 times over RAD+RE3, 3.3 times over RAD+RND, 3.8 times over RAD | Improved |
| Add MADE intrinsic reward to RAD | RAD · Pendulum-Swingup | return: around 800 in only 30K steps | Improved |
| Add MADE intrinsic reward to Dreamer | Dreamer · Hopper-Hop | return: more than 100 higher return than RE3 and 250 higher return than Dreamer | Improved |
| Replace the Hoeffding bonus with the MADE bonus | Value iteration, PPO with a model, and Q-learning · Bidirectional Lock | performance | Improved |
| Replace the Bernstein bonus with the MADE bonus | Value iteration, PPO with a model, and Q-learning · Bidirectional Lock | performance | Mixed |
| Add MADE regularization to policy gradient | Policy gradient · Chain MDP | convergence rate | Improved |
| Vary the recent-data buffer length (ablation) | MADE · DeepMind Control Suite tasks | performance | Mixed |
Closest papers by meaning
- Improving Intrinsic Exploration by Creating Stationary Objectives (ICLR 2024 · similarity 0.90)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.89)
- MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization (ICLR 2025 · similarity 0.88)
- Random Latent Exploration for Deep Reinforcement Learning (ICML 2024 · similarity 0.88)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 2025 · similarity 0.88)
- Uncertainty-Aware Reward-Free Exploration with General Function Approximation (ICML 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
