Research map / Reinforcement learning / Visual and representation RL
Discovered Policy Optimisation
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 |
|---|---|---|---|
| Use LPO instead of PPO | Policy optimisation · Brax environments (including environments unseen during meta-training) | evaluation return | Helped |
| Use DPO instead of PPO | Policy optimisation · Brax environments | evaluation return | Helped |
| Use DPO instead of PPO | Policy optimisation · MinAtar environments | evaluation return | Mixed |
| Learn the drift function from scratch rather than initialise it near PPO (ablation) | LPO · Brax environments | evaluation return | Hurt |
| Initialise the drift function near PPO (ablation) | Meta-learned policy optimisation · Brax environments | evaluation return | Helped |
| Add gradient spikes around ratio 1 to the analytic LPO model (ablation) | DPO-style analytic model of LPO · Brax environments | evaluation return | No clear effect |
Closest papers by meaning
- Can Learned Optimization Make Reinforcement Learning Less Difficult? (NeurIPS 2024 · similarity 0.90)
- Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator (NeurIPS 2024 · similarity 0.90)
- Discovering Temporally-Aware Reinforcement Learning Algorithms (ICLR 2024 · similarity 0.89)
- Reflective Policy Optimization (ICML 2024 · similarity 0.89)
- Operator World Models for Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning (ICLR 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.