AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning One Representation to Optimize All Rewards

Ahmed Touati, Yann Ollivier

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Learned state and action representations · 5 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
increase FB representation dimension dforward-backward (FB) representation · FetchReach and Ms. Pacman goal reachingsuccess rateImproved
small dimension d=25 instead of d=75FB representation · Discrete Mazepolicy quality ratioHurt
FB instead of goal-oriented DQNFB representation · all environmentssample efficiency (success rate vs epochs)No clear effect
FB instead of DQN+HERFB representation · Ms. Pacmanlearning speedImproved
goal-oriented DQN without HERDQN baseline · Ms. Pacmansuccess rateHurt

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