AI Paper Atlas

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

Addressing Function Approximation Error in Actor-Critic Methods

Scott Fujimoto, Herke Hoof, David Meger

ICML 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 2,316 citations (OpenAlex)

Read the paper

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
Remove delayed policy updates from TD3 (ablation)TD3 · HalfCheetah, Hopper, Walker2d, Antaverage return: TD3 / TD3 - DP: 9532.99 / 9590.65; 3304.75 / 2407.42; 4565.24 / 4695.50; 4185.06 / 3754.26Mixed
Remove target policy smoothing from TD3 (ablation)TD3 · HalfCheetah, Hopper, Walker2d, Antaverage return: TD3 / TD3 - TPS: 9532.99 / 8987.69; 3304.75 / 2392.59; 4565.24 / 4033.67; 4185.06 / 4155.24Mixed
Remove Clipped Double Q-learning from TD3 (ablation)TD3 · HalfCheetah, Hopper, Walker2d, Antaverage return: TD3 / TD3 - CDQ: 9532.99 / 9792.80; 3304.75 / 1837.32; 4565.24 / 2579.39; 4185.06 / 849.75Mixed
Add delayed policy updates to AHE (ablation)AHE · HalfCheetah, Hopper, Walker2d, Antaverage return: AHE / AHE + DP: 8401.02 / 7588.64; 1061.77 / 1465.11; 2362.13 / 2459.53; 564.07 / 896.13Mixed
Add target policy smoothing to AHE (ablation)AHE · HalfCheetah, Hopper, Walker2d, Antaverage return: AHE / AHE + TPS: 8401.02 / 9023.40; 1061.77 / 907.56; 2362.13 / 2961.36; 564.07 / 872.17Mixed
Add Clipped Double Q-learning to AHE (ablation)AHE · HalfCheetah, Hopper, Walker2d, Antaverage return: AHE / AHE + CDQ: 8401.02 / 6470.20; 1061.77 / 1134.14; 2362.13 / 3979.21; 564.07 / 3818.71Mixed
Use Clipped Double Q-learning rather than the actor-critic Double Q-learning variant (ablation)TD3 · HalfCheetah, Hopper, Walker2d, Antaverage return: TD3 / DQ-AC: 9532.99 / 9433.87; 3304.75 / 1773.71; 4565.24 / 3100.45; 4185.06 / 2445.97Mixed
Use Clipped Double Q-learning rather than the actor-critic Double DQN variant (ablation)TD3 · HalfCheetah, Hopper, Walker2d, Antaverage return: TD3 / DDQN-AC: 9532.99 / 10306.90; 3304.75 / 2155.75; 4565.24 / 3116.81; 4185.06 / 1092.18Mixed

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