Research map / Reinforcement learning / Visual and representation RL
Evolving Reinforcement Learning Algorithms
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the learned Q-value regularizer used by GraphSeven to DQN | DQN · Asteroid | score: 2097.5 -> 2390.4 | Helped |
| Add the learned Q-value regularizer used by GraphSeven to DQN | DQN · Bowling | score: 68.1 -> 80.5 | Helped |
| Add the learned Q-value regularizer used by GraphSeven to DQN | DQN · Boxing | score: 94.6 -> 100.0 | Helped |
| Add the learned Q-value regularizer used by GraphSeven to DQN | DQN · RoadRunner | score: 44127.0 -> 65516.0 | Helped |
| Bootstrap the evolutionary search from DQN instead of initializing algorithms from scratch (ablation) | Evolving RL Algorithms · Five training environments | final meta-training performance: 40% | Helped |
| Train from scratch on CartPole and LunarLander instead of CartPole alone (ablation) | Evolving RL Algorithms · CartPole and LunarLander training; generalization to other environments | generalization | Helped |
Closest papers by meaning
- Distributional Meta-Gradient Reinforcement Learning (ICLR 2023 · similarity 0.90)
- Meta-Gradient Reinforcement Learning with an Objective Discovered Online (NeurIPS 2020 · similarity 0.90)
- Can Learned Optimization Make Reinforcement Learning Less Difficult? (NeurIPS 2024 · similarity 0.89)
- Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator (NeurIPS 2024 · similarity 0.89)
- MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning (ICLR 2024 · similarity 0.88)
- AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers (NeurIPS 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.