Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
Bibliographic record
Abstract
Multi-agent reinforcement learning (MARL) enables systems of autonomous agents to solve complex tasks from jointly gathered experiences of the environment. Many MARL algorithms perform centralised training (CT), often in a simulated environment, where at each time-step the critic makes use of a single sample of the agents' joint-action for training. Yet, as agents update their policies during training, these single samples may poorly represent the agents' joint-policy leading to high variance gradient estimates that hinder learning. In this paper, we examine the effect on MARL estimators of allowing the number of joint-action samples taken at each time-step to be greater than 1 in training. Our theoretical analysis shows that even modestly increasing the number of joint-action samples shown to the critic leads to TD updates that closely approximate the true expected value under the current joint-policy. In particular, we prove this reduces variance in value estimates similar to that of decentralised training while maintaining the learning benefits of CT. We describe how such a protocol can be seamlessly realised by sharing policy parameters between the agents during training and apply the technique to induce lower variance in estimates in MARL methods within a general apparatus which we call Performance Enhancing Reinforcement Learning Apparatus (PERLA). Lastly, we demonstrate PERLA's performance improvements and estimator variance reduction capabilities in a range of environments including Multi-agent Mujoco, and StarCraft II.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".