Research map / Reinforcement learning / Visual and representation RL
Representation-Driven Reinforcement Learning
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 |
|---|---|---|---|
| Representation-driven exploration (RepES) vs. standard evolution strategy (ES) on standard MuJoCo suitcase task | RepES (RepRL ES variant) · MuJoCo suitcase | return during training | Mixed |
| Representation-driven ES with sparse goal-reward MuJoCo variant (control cost penalizes staying still) | RepES (RepRL ES variant) · Sparse MuJoCo | goal attainment / return | Helped |
| RepRL as a regularizer on PPO policy gradient | RepPG (PPO + RepRL regularizer) · MinAtar | return during training | Helped |
| Decision set type: policy space vs. latent space vs. history-based (ablation) | RepES · Sparse HalfCheetah | return | No clear effect |
| Inner trajectory sampling (sampling from states along trajectory with discount) vs. sampling from initial states | RepRL · text-only, no experiment reported | value estimate | No clear effect |
Closest papers by meaning
- Learning Actionable Representations with Goal Conditioned Policies (ICLR 2019 · similarity 0.92)
- Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning (ICLR 2025 · similarity 0.89)
- Reward-Aware Proto-Representations in Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction (ICLR 2025 · similarity 0.88)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.88)
- Cross-Domain Policy Adaptation by Capturing Representation Mismatch (ICML 2024 · similarity 0.87)
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.