Research map / Reinforcement learning / Visual and representation RL
Composing Task-Agnostic Policies with Deep Reinforcement Learning
Ahmed H. Qureshi, Jacob J. Johnson, Yuzhe Qin, Taylor Henderson, Byron Boots, Michael C. Yip
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 |
|---|---|---|---|
| Use the composed policy instead of the strongest standard-RL baseline | Ant Random Goal · Ant Random Goal | distance: 0.21 \pm 0.08 -> 0.11 \pm 0.05 | Improved |
| Use the composed policy instead of the strongest standard-RL baseline | Ant Cross Maze · Ant Cross Maze | distance: 0.78 \pm 0.06 -> 0.11 \pm 0.02 | Improved |
| Use the composed policy instead of the strongest standard-RL baseline | Pusher · Pusher | distance: 0.17 \pm 0.02 -> 0.14 \pm 0.02 | Improved |
| Use the composed policy instead of the strongest standard-RL baseline | HalfCheetah Hurdle · HalfCheetah Hurdle | distance: 0.79 \pm 0.01 -> 0.27 \pm 0.22 | Improved |
| Add the attention network (ablation) | Composition-SAC · Ant Random Goal, Ant Cross Maze, and Pusher | distance | Improved |
| Add the BRNN skill encoder (ablation) | Composition-SAC · Ant Random Goal, Ant Cross Maze, and Pusher | distance | Improved |
| Add both the attention network and BRNN skill encoder (ablation) | Composition-SAC · Ant Random Goal, Ant Cross Maze, and Pusher | distance | Improved |
Closest papers by meaning
- Synthesized Policies for Transfer and Adaptation across Tasks and Environments (NeurIPS 2018 · similarity 0.89)
- Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement (ICML 2018 · similarity 0.88)
- Solving Compositional Reinforcement Learning Problems via Task Reduction (ICLR 2021 · similarity 0.88)
- Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning (ICML 2025 · 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.
