AI Paper Atlas

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

Policy Search by Target Distribution Learning for Continuous Control

Chuheng Zhang, Yuanqi Li, Jian Li

AAAI 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Trajectory reuse in policy gradients · 6 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
Use TDL instead of PPOContinuous control policy learning · MuJoCo taskscumulative rewardMixed
Use TDL-ESr instead of the other compared methodsContinuous control policy learning · MuJoCo taskscumulative rewardImproved
Set target distributions rather than directly updating the policy with stochastic gradient ascent (ablation)TDL-ES · MuJoCo taskscumulative rewardImproved
Increase on-policy sample reuse (ablation)TDL-direct, TDL-ES, and TDL-ESr · Hopper-v2performanceNo clear effect
Increase on-policy sample reuse (ablation)PPO · Hopper-v2performanceHurt
Use an entropy term (ablation)PPO · Simple one-step cost environmentasymptotic performanceHurt
Impose a minimum variance threshold (ablation)PPO · Simple one-step cost environmentcostImproved
Impose a minimum variance threshold (ablation)PPO · Simple one-step cost environmenttraining stabilityNo clear effect
Use a smaller clipping constant (ablation)PPO · Simple one-step cost environmenttraining stabilityNo clear effect
Move the target mean in the negative direction for negative-advantage samples (ablation)TDL-direct · MuJoCo tasksexplorationImproved
Move the target mean in the negative direction for negative-advantage samples (ablation)TDL-direct · Humanoidcumulative rewardHurt
Move the target mean in the negative direction for negative-advantage samples (ablation)TDL-ES · MuJoCo taskstraining stabilityHurt

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