VolleyBench

Description

VolleyBench is an environment for building machine learning models of international volleyball and trading those models on historical betting markets. Agents develop ML strategies using historical match data from Women's Volleyball World Championships, place bets on match outcomes, and manage bankroll across a 1-year window of tournament play.

Capabilities

• Developing machine learning models for volleyball match prediction
• Analyzing team performance and historical matchup data
• Backtesting models against historical betting odds
• Bankroll management and bet execution

Compute Requirements

Agents are given a sandbox with file system access and scientific Python libraries (pandas, numpy).

Tasks

There is one split in this environment:

• Train: 3 scenarios

Each scenario covers a 1-year window of volleyball tournament play.

Reward Structure

This is a dense, verifiable reward environment. Rewards occur after each matchday. The reward is calculated as the difference in log wealth before and after betting, i.e:

$\log{W_{t+1}} - \log{W_{t}}$

Agents must place at least one bet per matchday. No LLM graders are used -- reward is deterministic based on match outcomes.

Data

Historical volleyball match data from Women's Volleyball World Championships including team names, scores, betting odds, and match results. Training data is mounted at /tmp/gr-datasets for agents to build models.

Tools

Agents are given access to CLI tools (bash, read, write, edit, multi_edit, grep, glob, ls, todo_write) plus 4 environment-specific tools:

Time Horizon

VolleyBench is an open-ended, long-horizon environment where agents simulate a year of model development and betting across international volleyball tournaments.

Environment Difficulty

[Put environment difficulty statistics here]

Other Environment Requirements

There are no further environment requirements; VolleyBench works out of the box with the OpenReward endpoint without any external API keys.

Safety

Agents in VolleyBench are told to maximize their long-run bankroll growth. The environment does not present direct safety risks, as agents only interact with historical data through betting decisions on public odds.

There may be indirect risks, however, in that an agent that is taught to maximize long-run wealth may blindly follow this objective when tested in other environments, leading it to pursue unethical objectives. Our advice is that multi-environment training runs involving VolleyBench should include other environments that teach agents to respect ethical norms so that the agent understands a broader category of objectives than just maximizing wealth.

Citation

@dataset{GRVolleyBench,
  author    = {General Reasoning Inc. Team},
  title     = {VolleyBench},
  year      = {2026},
  publisher = {OpenReward},
  url       = {https://www.openreward.ai/GeneralReasoning/VolleyBench}
}