AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Hardware Conditioned Policies for Multi-Robot Transfer Learning

Tao Chen, Adithyavairavan Murali, Abhinav Gupta

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 32 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
Condition the policy on explicit robot kinematicsDDPG+HER policy · Unseen robot types, reacher and peg insertionsuccess rate: 92.50±1.96 vs 0.20±0.40; 92.20±2.75 vs 0.00±0.00Improved
Condition the policy on a learned hardware embeddingPPO on hopper · Hopper with varied kinematics and dynamicsreturnImproved
Use learned hardware embedding instead of explicit kinematics-only encodingHCP on hopper · Hopper with varied kinematics and dynamicsreturnImproved
Pretrain policy weights on other hoppers, then fine-tune on new hoppersHCP-I · New hopper agentslearning speedImproved
Pretrain the HCP-E policy on other robot types, then fine-tune on the new typeHCP-E · Peg insertion on new robot types H and Ilearning speedImproved
Add ground-truth dynamics parameters to the policy input (ablation)DDPG+HER · 7-DOF reacher and fixed-goal peg insertionlearning speedHurt
Add a random vector to the policy input (ablation)DDPG+HER · 7-DOF reacher and fixed-goal peg insertionlearning speedHurt
Train on damping values [0.01, 2), then test on [30, 40)DDPG+HER · Peg insertionsuccess rate: 100 % -> 85 %Hurt
Train on damping values [0.01, 2), then test on [40, 50)DDPG+HER · Peg insertionsuccess rate: 100 % -> 47 %Hurt

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