AI Paper Atlas

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

Maximum a Posteriori Policy Optimisation

Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Remi Munos, Nicolas Heess, Martin Riedmiller

ICLR 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 225 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
Use MPO instead of PPOcontinuous control tasks in the Control Suite · Control Suitesample efficiencyImproved
Use MPO instead of DDPGcontinuous control tasks in the Control Suite · Control Suitesample efficiencyImproved
Replace non-parametric variational distribution with a parametric one (ablation)MPO · Acrobot, Walker-2D, Hoppersample efficiencyHurt
Replace the automatically tuned KL constraint with a manually set entropy regulariser (ablation)MPO / EPG + Retrace · Acrobot, Walker-2D, Hopperhyperparameter robustnessHurt
Use a single action sample to estimate the action integral (ablation)off-policy actor-critic with Retrace · Acrobot, Walker-2D, HopperperformanceHurt
Use MPO instead of PPOWalker-2D parkour · Walker-2D parkourtrajectories to find a good policy: approximately 1M trajectories -> about 70k trajectoriesImproved
Use MPO instead of PPOWalker-2D parkour · Walker-2D parkoursamples to find a good policy: 60M samplesImproved
Use MPO instead of C51MPO · Breakoutscore: 748 -> 360.5Hurt
Use MPO instead of C51MPO · Q*bertscore: 23,784 -> 10,317.0Hurt
Use MPO instead of C51MPO · Tennisscore: 23.1 -> 22.2Hurt
Use MPO instead of Prior. DuelingMPO · Boxingscore: 98.9 -> 82.0Hurt

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