AI Paper Atlas

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

Q-functionals for Value-Based Continuous Control

Samuel Lobel, Sreehari Rammohan, Bowen He, Shangqun Yu, George Konidaris

AAAI 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 7 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 policy-network action selection with choosing the best of 1,000 random actionsQ-functional on LunarLanderContinuous-v2 · LunarLanderContinuous-v2fraction of states where selected action beats one random action: 99.9%Improved
Use the trained DDPG policy for action selection rather than random samplingDDPG on LunarLanderContinuous-v2 · LunarLanderContinuous-v2fraction of states where selected action is below a random action: 15%Hurt
Replace repeated state-action network evaluations with a rank 3 Legendre Q-functionalQ-value evaluation on Hopper · Hopperaction-evaluation speed: 3.5 timesImproved
Precompute action basis representations (ablation)Q-functionals · Hopperaction-evaluation speed: more than 20 timesImproved
Precompute action basis representations (ablation)Q-functionals · continuous-control tasksreinforcement-learning behaviorNo clear effect
Increase the number of samples used to select the maximum-value action (ablation)Q-functional on Humanoid-v2 · Humanoid-v2performance: 1,000Improved
Represent a policy with a Q-value-derived distribution instead of a squashed GaussianQ-functional versus SAC on the bandit task · bandit taskability to represent a bimodal optimal policyImproved

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