Research map / Reinforcement learning / Visual and representation RL
Generalized Hidden Parameter MDPs:Transferable Model-Based RL in a Handful of Trials
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 |
|---|---|---|---|
| Train a joint or structured latent-variable model across tasks instead of training a Specialist separately for each task | MuJoCo Ant tasks · DirectionAnt and CrippledLegDirectionAnt | sample efficiency | Helped |
| Add latent variables to the ensemble model to represent task variation | MuJoCo Ant tasks · DirectionAnt and CrippledLegDirectionAnt | episode reward | Helped |
| Use a latent-variable model rather than PEARL | MuJoCo Ant tasks · DirectionAnt and CrippledLegDirectionAnt | sample efficiency: >10× | Helped |
| Use a joint or structured latent-variable model rather than PEARL | MuJoCo Ant tasks · CrippledLegDirectionAnt novel combinations | episode reward | Helped |
| Use structured latent variables rather than a joint latent variable | GHP-MDP · CrippledLegDirectionAnt novel combinations | episode reward | No clear effect |
| Use structured latent variables rather than a joint latent variable | GHP-MDP · DirectionAnt and CrippledLegDirectionAnt novel directions | episode reward | Helped |
| Train PEARL on 40 tasks rather than the smaller task set | PEARL · DirectionAnt and CrippledLegDirectionAnt training | episode reward | No clear effect |
| Train PEARL on more tasks | PEARL · DirectionAnt and CrippledLegDirectionAnt novel directions | episode reward | Hurt |
Closest papers by meaning
- Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models (NeurIPS 2025 · similarity 0.88)
- A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals (ICLR 2025 · similarity 0.87)
- Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · similarity 0.87)
- Reward Machines for Deep RL in Noisy and Uncertain Environments (NeurIPS 2024 · similarity 0.87)
- Transfer Q-Learning with Composite MDP Structures (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.