AGENT SKILL

offline-bandits-data

Use AgileRL offline RL datasets, replay/data conversion, CQL/ILQL, contextual bandits, NeuralUCB/NeuralTS, and BanditEnv workflows.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
offline-bandits-data
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Use AgileRL offline RL datasets, replay/data conversion, CQL/ILQL, contextual bandits, NeuralUCB/NeuralTS, and BanditEnv workflows.
disable-model-invocation
true

02 资源文件 5

03 SKILL.md 正文

AgileRL Offline RL And Bandit Data

Use this sub-skill for AgileRL offline reinforcement learning, replay/data conversion, CQL, ILQL, train_offline, contextual bandits, NeuralUCB, NeuralTS, and BanditEnv workflows.

Read First

  • references/workflows.md for offline RL and contextual bandit recipes.
  • references/data-formats.md for transition, HDF5/Minari, and tabular bandit schemas.
  • references/api-reference.md for replay/bandit/offline APIs.
  • references/troubleshooting.md for shape, schema, and network/download failures.
  • scripts/inspect_bandit_setup.py --help for a no-download synthetic bandit probe.

Boundaries

  • Use ../training-workflows/SKILL.md for online Gymnasium PPO/DQN/DDPG/TD3 workflows.
  • Use ../hpo-and-mutation/SKILL.md for tournament/mutation configuration.
  • Use ../llm-fine-tuning/SKILL.md for language/LLM datasets and RL post-training environments.
  • This sub-skill owns static transition datasets, replay filling, Minari/HDF5 handling, and one-step contextual bandit datasets.

Offline RL Flow

  1. Load or validate a dataset with observations, actions, rewards, next observations, and done/terminal flags.
  2. Create an environment only for spaces/evaluation, not online data collection.
  3. Create a CQN/ILQL-style population with create_population(...).
  4. Fill ReplayBuffer with Transition(...).to_tensordict() entries.
  5. Configure HPO and call train_offline(...) or a custom offline loop.

Contextual Bandit Flow

  1. Prepare tabular or array features and targets.
  2. Create BanditEnv(features, targets).
  3. Use NeuralUCB or NeuralTS with a discrete action space.
  4. Use replay memory and train_bandits(...) or a custom one-step loop.

Safe Validation

python scripts/inspect_bandit_setup.py --rows 8 --features 4 --arms 3

The helper creates synthetic in-memory data. It does not download UCI datasets or run training.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351