AI Paper Atlas

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

Adversarially Guided Actor-Critic

Yannis Flet-Berliac, Johan Ferret, Olivier Pietquin, Philippe Preux, Matthieu Geist

ICLR 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory · 14 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 an adversary-prediction discrepancy bonus without episodic countPPO actor-critic · VizDoomaverage return: 0.74 ± 0.05 vs 0. at 2M timesteps; 0.96 ± 0.001 vs 0.95 ± 0.001 at 6M timestepsImproved
Add the adversarial exploration objectivePPO actor-critic · KC-S4R3final average performance: 0.95 vs 0.54Improved
Add the adversarial exploration objectivePPO actor-critic · KC-S5R3final average performance: 0.93 vs 0.Improved
Add the adversarial exploration objectivePPO actor-critic · MR-N10S10final average performance: 0.52 vs 0.40Improved
Add the adversarial exploration objectivePPO actor-critic · OM-2Dlhbfinal average performance: 0.64 vs 0.20Improved
Add the adversarial exploration objectivePPO actor-critic · OM-1Qfinal average performance: 0.78 vs 0.Improved
Add the adversarial exploration objectivePPO actor-critic · OM-2Qfinal average performance: 0.63 vs 0.Improved
Train with the adversarial objective but no extrinsic rewardAGAC · MultiRoomN10S6average return: ~ 0.15 vs zero average return for random agentsImproved
Use a smaller learning rate for the adversary than for the actorAGAC · KeyCorridorS4R3average returnImproved
Vary the adversarial bonus coefficient c from its selected value (ablation)AGAC · KeyCorridorS4R3average returnHurt
Vary the actor-to-adversary learning-rate ratio ν from its selected value (ablation)AGAC · KeyCorridorS4R3average returnHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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