marvinandClaude Opus 5.5
fde8e2fb2e
The sum of all bids may never equal the number of cards each player holds in the round; the last bidder has to adjust their bid. This was an optional "not equal" lobby setting and is now a fixed rule of the game engine, so it applies to humans, AI players and training alike. - Remove GameOptions.not_equal, the set_options field, the lobby toggle and the --not-equal training flag - Explain the rule in the lobby and show the blocked bid while bidding - Drop the option from the AI observation encoding - Tests check that no round ends with bids summing to the cards in hand Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
wizard_ai
AI player for the Wizard server. The actual RL model is still to be implemented; this package provides everything around it.
agents/—Agentinterface (act(observation) -> action) plusRandomAgent,HeuristicAgent(baseline / fallback) andModelAgent(wraps aPolicy)model/encoding.py— observation → fixed-size feature vector (FEATURE_SIZE), and the fixed action space (21 bids + 60 cards + 4 trump suits) with legal-action masks; works for 3–6 playersmodel/policy.py— the place to plug in the model: subclassPolicy, implementselect,update,save_weights/load, register with@register_policy.UniformPolicyis a placeholder so the pipeline runs end to end.training/env.py— turn-based multi-agent environment aroundwizard_game(reward = score change per round / 100)training/self_play.py— self-play loop collecting per-player trajectories and callingPolicy.update, with checkpointingtraining/evaluate.py— play agents against each other (mean score, win rate)service/client.py— production: connects tows://wizard_server:8083/internal/ai, answersdeciderequests, reconnects automatically
pip install -r requirements-dev.txt
python -m wizard_ai train --episodes 5000 --out models/latest
python -m wizard_ai evaluate --agents model,heuristic,random,random --games 200
python -m wizard_ai serve # env: SERVER_URL, AI_SHARED_SECRET, AGENT, MODEL_PATH
pytest