HFEPX · Eval paper review
Ruize Zhang, Sirui Xiang, Zelai Xu, Feng Gao +5 more
Published
May 7, 2025
Citations
0
Trust level
Moderate
Usefulness score
65/100 (Medium)
Extraction confidence
70% (Moderate)
Derived from extracted protocol signals and abstract evidence.
Rater population
Domain Experts
Signals refreshed
Feb 26, 2026
This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.
Use this for comparison and orientation, not as your only source.
Best use
Secondary protocol comparison source
Use if you need
A secondary eval reference to pair with stronger protocol papers.
What to verify
Validate the evaluation procedure and quality controls in the full paper before operational use.
Main weakness
No major weakness surfaced.
Useful as a secondary reference; validate protocol details against neighboring papers.
If you are doing eval pipeline work, start here
In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control. The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to its long-horizon dependencies, tight inter-agent coupling, and the underactuated dynamics of quadrotors. To address this, we propose Hierarchical Co-Self-Play (HCSP), a hierarchical reinforcement learning framework that separates centralized high-level strategic decision-making from decentralized low-level motion control. We design a three-stage population-based training pipeline to enable both strategy and skill to emerge from scratch without expert demonstrations: (I) training diverse low-level skills, (II) learning high-level strategy via self-play with fixed low-level skills, and (III) joint fine-tuning through co-self-play. Experiments show that HCSP achieves superior performance, outperforming non-hierarchical self-play and rule-based hierarchical baselines with an average 82.9% win rate and a 71.5% win rate against the two-stage variant. Moreover, co-self-play leads to emergent team behaviors such as role switching and coordinated formations, demonstrating the effectiveness of our hierarchical design and training scheme. The project page is at https://hi-co-self-play.github.io.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
Demonstrations
Directly usable for protocol triage.
"We design a three-stage population-based training pipeline to enable both strategy and skill to emerge from scratch without expert demonstrations: (I) training diverse low-level skills, (II) learning high-level strategy via self-play with fixed low-level skills, and (III) joint fine-tuning through co-self-play."
Automatic Metrics
Includes extracted eval setup.
"In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control."
Not reported
No explicit QC controls found.
"In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control."
Not extracted
No benchmark anchors detected.
"In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control."
Win rate
Useful for evaluation criteria comparison.
"Experiments show that HCSP achieves superior performance, outperforming non-hierarchical self-play and rule-based hierarchical baselines with an average 82.9% win rate and a 71.5% win rate against the two-stage variant."
Domain Experts
Helpful for staffing comparability.
"We design a three-stage population-based training pipeline to enable both strategy and skill to emerge from scratch without expert demonstrations: (I) training diverse low-level skills, (II) learning high-level strategy via self-play with fixed low-level skills, and (III) joint fine-tuning through co-self-play."
No benchmark or dataset names were extracted from the available abstract.
In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
Detected: Demonstrations
Evaluation mode is explicit
Detected: Automatic Metrics
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
Metric reporting is present
Detected: win rate
