Research map / Reinforcement learning / Visual and representation RL
Learning One Representation to Optimize All Rewards
Ahmed Touati, Yann Ollivier
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 |
|---|---|---|---|
| increase FB representation dimension d | forward-backward (FB) representation · FetchReach and Ms. Pacman goal reaching | success rate | Improved |
| small dimension d=25 instead of d=75 | FB representation · Discrete Maze | policy quality ratio | Hurt |
| FB instead of goal-oriented DQN | FB representation · all environments | sample efficiency (success rate vs epochs) | No clear effect |
| FB instead of DQN+HER | FB representation · Ms. Pacman | learning speed | Improved |
| goal-oriented DQN without HER | DQN baseline · Ms. Pacman | success rate | Hurt |
Closest papers by meaning
- Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings (ICML 2024 · similarity 0.89)
- Foundation Policies with Hilbert Representations (ICML 2024 · similarity 0.88)
- Learning Goal-Conditioned Representations for Language Reward Models (NeurIPS 2024 · similarity 0.88)
- Learning Process Rewards via Visitation Matching for Efficient RL (NeurIPS 2026 · similarity 0.88)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · 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.
