AI Paper Atlas

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

Reward-Adaptive Reinforcement Learning: Dynamic Policy Gradient Optimization for Bipedal Locomotion

Changxin Huang, Guangrun Wang, Zhibo Zhou, Ronghui Zhang, Liang Lin

TPAMI 2022 · Reinforcement learning › Policy gradient and actor-critic · approach: Policy gradients for special settings · 54 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
add multi-head critic (separate value per reward component) (ablation)DDPG · Gazebo biped trainingepisodes until reward rises: 6k -> 4k episodesImproved
add dynamic priority weights to multi-head critic (ablation)MHDDPG · Gazebo biped trainingepisodes until reward rises: 4k -> 2k episodesImproved
add multi-head critic (ablation)DDPG · Walker2d-v3mean return: 2398.5 -> 3162.0Improved
add dynamic weight (ablation)MHDDPG · Walker2d-v3mean return: 3162.0 -> 3217.5No clear effect
add multi-head critic (ablation)DDPG · Hopper-v3mean return: 3476.5 -> 3539.3Improved
add dynamic weight (ablation)MHDDPG · Hopper-v3mean return: 3539.3 -> 3600.4Improved
add multi-head critic (ablation)DDPG · HalfCheetah-v3mean return: 12422.9 -> 12748.9Improved
add dynamic weight (ablation)MHDDPG · HalfCheetah-v3mean return: 12748.9 -> 12895.3Improved
add hybrid dynamic policy gradientPPO · Hopper-v3mean return: 2609.3 -> 3263.5Improved
add hybrid dynamic policy gradientPPO · Walker2d-v3mean return: 3588.5 -> 4688.0Improved
add hybrid dynamic policy gradientPPO · HalfCheetah-v3mean return: 5783.9 -> 6165.2Improved
add multi-head critic (ablation)DDPG · Gazebo slope walkingsuccess rateNo clear effect

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