AI Paper Atlas

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

Deep Conservative Policy Iteration

Nino Vieillard, Olivier Pietquin, Matthieu Geist

AAAI 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Tree search and policy optimization · 10 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 CPI-style stochastic policy mixtures with α0=0.1DQN on Cartpole · Cartpole (500-step)average episode score: 300 -> 480Improved
add CPI-style stochastic policy mixtures with α0=0.1DQN on Cartpole · Cartpole (500-step)standard deviation of score: approximately 200 -> around 20Improved
use a constant small mixture rate (α0=0.001) (ablation)DCPI on Cartpole · Cartpole (500-step)stabilityImproved
use a constant higher mixture rate (ablation)DCPI on Cartpole · Cartpole (500-step)stabilityHurt
replace a fixed mixture rate with an adaptive mixture rate (ablation)DCPI on Cartpole · Cartpole (500-step)convergence speed and stabilityImproved
set the mixture rate to α=1, removing conservative mixing (ablation)DCPI on Cartpole · Cartpole (500-step)stabilityImproved
use the SPI adaptive rate, clipped between 0 and 1 (ablation)DCPI on Cartpole · Cartpole (500-step)training behaviorNo clear effect
use the Adamax adaptive mixture rate (ablation)DCPI on Cartpole · Cartpole (500-step)convergence speed and stabilityMixed
use the CPI adaptive rate with α0=0.1 (ablation)DCPI on Cartpole · Cartpole (500-step)average episode score: 300 -> 480Improved
act with an ε-greedy policy derived from qθ rather than πω (ablation)DCPI on Atari · AtariperformanceImproved
add the DCPI conservative actor and adaptive mixture rateDQN on Atari · Atari (20-game subset)games outperforming DQN: 15 games over 20Improved
use a conservative mixture rateDQN on Atari · Atarilearning stabilityNo 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