Papers › Mean Actor Critic

Mean Actor Critic

1 Sep 2017arXiv:1709.00503archive 2025-07-28

Cameron Allen, Kavosh Asadi, Melrose Roderick, Abdel-rahman Mohamed, George Konidaris, Michael Littman

We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient of the policy, rather than using only the actions that were actually executed. We prove that this approach reduces variance in the policy gradient estimate relative to traditional actor-critic methods. We show empirical results on two control domains and on six Atari games, where MAC is competitive with state-of-the-art policy search algorithms.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

camall3n/atari-MAC mentioned on GitHubtf report
kavosh8/MAC mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Atari GamesReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Beam Rider MAC Score 6072 #38 of 49 Archive leaderboard report
Atari Games Atari 2600 Breakout MAC Score 372.7 #30 of 58 Archive leaderboard report
Atari Games Atari 2600 Pong MAC Score 10.6 #47 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert MAC Score 243.4 #54 of 57 Archive leaderboard report
Atari Games Atari 2600 Seaquest MAC Score 1703.4 #43 of 57 Archive leaderboard report
Atari Games Atari 2600 Space Invaders MAC Score 1173.1 #44 of 55 Archive leaderboard report
Continuous Control Cart Pole (OpenAI Gym) MAC Score 178.3 #1 of 1 Archive leaderboard report
Continuous Control Lunar Lander (OpenAI Gym) MAC Score 163.5 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections