AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Learning Guidance Rewards with Trajectory-space Smoothing

Tanmay Gangwani, Yuan Zhou, Jian Peng

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 4 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
replace environmental rewards with IRCR guidance rewardsSAC · Peg insertionperformance: $104 \scriptstyle{\pm 4}$ -> $160 \scriptstyle{\pm 7}$Improved
replace environmental rewards with IRCR guidance rewardsTD3 · Hopperperformance: $235 \scriptstyle{\pm 37}$ -> $2981 \scriptstyle{\pm 114}$Improved
replace environmental rewards with IRCR guidance rewardsTD3 · Half-Cheetahperformance: $-123 \scriptstyle{\pm 50}$ -> $6844 \scriptstyle{\pm 918}$Improved
use n-step returns (n=10) instead of one-step returnsSAC with environmental rewards · Hopper and Half-Cheetahperformance: $626 \scriptstyle{\pm 281}$ on Hopper; $-42 \scriptstyle{\pm 29}$ on Half-CheetahNo clear effect
use λ-returns (λ=0.9) instead of one-step returnsSAC with environmental rewards · Hopper and Half-Cheetahperformance: $566 \scriptstyle{\pm 101}$ on Hopper; $-112 \scriptstyle{\pm 206}$ on Half-CheetahNo clear effect
replace environmental rewards with guidance rewardsSAC · MuJoCo locomotion tasks with episodic rewardssample efficiencyImproved
replace environmental rewards with guidance rewardsMA-TD3 · Rover Domain, coupling factors 1–4percentage of POIs harvestedImproved
use IRCR guidance rewards with distributional C51MA-C51 · Rover Domainpercentage of POIs harvestedImproved

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