AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Synthesized Policies for Transfer and Adaptation across Tasks and Environments

Hexiang Hu, Liyu Chen, Boqing Gong, Fei Sha

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 11 citations (OpenAlex)

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 changedWhereMeasuredEffect
compose policy from environment and task embeddings via shared basis (SynPo) instead of MLP on concatenated embeddingsimitation-learned agent · GridWorld unseen pairsAvgSR: 66.1 ± 2.6% -> 82.1 ± 1.5%Improved
model environment embeddings (SynPo) instead of ignoring environments (MTL) (ablation)policy network · GridWorld unseen pairsAvgSR: 41.5 ± 1.4% -> 82.1 ± 1.5%Improved
reduce agent view window to 1x1 cellMTL baseline · GridWorld unseen pairsAvgSR: 41.5 -> 6.1Hurt
increase fraction of seen pairs beyond 40% of all pairs (ablation)SynPo · GridWorld 10 envs x 10 tasksAvgSR on unseenNo clear effect
fine-tune with PPO reinforcement learning after imitationSynPo · GridWorld unseen pairsAvgSR: 82.1 -> 96.16%Improved
fine-tune with PPO instead of imitation onlyMLP · GridWorld unseen pairsAvgSRImproved
transfer to unseen environments or tasks (setting 3, both new) instead of one new (setting 2)SynPo · GridWorld cross pair (Q's env, P's task)AvgSR: 50.5% -> 42.7%Hurt
use SynPo instead of MLP when transferring to unseen environments/taskspolicy network · GridWorld transfer setting 2, cross pair (Q's env, P's task)AvgSR: 13.8% -> 50.5%Improved
use SynPo instead of MLP, cross pair (P's env, Q's task)policy network · GridWorld transfer setting 2AvgSR: 20.7% -> 21.5%No clear effect
use SynPo instead of MTL, ModuleNet, MLPpolicy network · THOR unseen pairsAvgSR: 33.3% -> 35.4%Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy