AGENT SKILL

evaluation

Evaluate pretrained PPO checkpoints, resolve checkpoint/environment configuration, and diagnose load or render issues.

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

01 前言 Front Matter

name
evaluation
license
MIT
metadata
{ "disco-role": "operating" }
description
Evaluate pretrained PPO checkpoints, resolve checkpoint/environment configuration, and diagnose load or render issues.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Evaluation

Use this sub-skill when the user asks to test a pretrained network, evaluate a checkpoint, render a trained policy, average episode rewards, or understand why a PPO checkpoint load fails.

Do not use this sub-skill for training-loop changes, PPO update debugging, reward-log plotting, or GIF composition. Route log plots and frame/GIF workflows to the sibling visualization sub-skill. Route low-level PPO.load, PPO.save, select_action, and architecture questions to the root shared API reference.

What this sub-skill owns

  • Resolving the pretrained checkpoint path convention: PPO_preTrained/<env_name>/PPO_<env_name>_<random_seed>_<run_num>.pth.
  • Matching checkpoint names to environment names, action-space class, and PPO constructor dimensions.
  • Preserving continuous-policy action_std alignment; the repo's checkpoint files do not store action_std.
  • Running or adapting the test.py evaluation pattern: load policy, run episodes, print per-episode rewards, and report the average reward.
  • Deciding whether rendering is safe in local, notebook, remote, or headless sessions.
  • Diagnosing missing Gym/Roboschool dependencies, checkpoint path mistakes, Gym/Gymnasium API drift, and state-dict shape mismatches.

Quick workflow

  1. Resolve the intended checkpoint before running an environment. Use the bundled helper from this sub-skill directory:

    python scripts/evaluation_config_helper.py --list-presets
    python scripts/evaluation_config_helper.py \
      --env-name RoboschoolWalker2d-v1 \
      --checkpoint-root PPO_preTrained \
      --check-file
    

    The helper is path/configuration-only by default. It does not import gym, roboschool, or the PPO module and does not run rollouts.

  2. Match the live environment to the checkpoint. The environment used for gym.make(env_name) must expose the same observation dimension, action dimension, and action-space type that were used to save the state dict. A checkpoint named for CartPole-v1 is not load-compatible with LunarLander-v2, and a discrete checkpoint is not compatible with a continuous Box policy.

  3. Construct the PPO agent with evaluation-compatible arguments. The original testing script uses lr_actor=0.0003, lr_critic=0.001, gamma=0.99, eps_clip=0.2, and K_epochs=80. These update hyperparameters are mostly inert during pure select_action evaluation, but the constructor still requires them. Continuous policies also require an action_std float at construction time.

  4. Load the checkpoint once the dimensions are known. The shared PPO implementation saves policy_old.state_dict() and load(checkpoint_path) loads the same state dict into both policy_old and policy using torch.load(..., map_location=...). Use the root API reference for exact load/save behavior.

  5. Run episodes and average rewards. The native evaluation loop resets the env, calls ppo_agent.select_action(state), steps the env until done or max_ep_len, clears the rollout buffer after each episode, prints episode reward, and reports average test reward over total_test_episodes.

  6. Render only when the display path is ready. Numeric evaluation does not require rendering. For on-screen display, use a compatible Gym render path and a real display. For rgb_array frame capture and GIF assembly, switch to visualization.

Core references

  • Evaluation workflow - evaluation loop adaptation, old/new Gym API handling, and render choices.
  • Checkpoints and environments - file naming, built-in pretrained environment presets, and action-space matching rules.
  • Troubleshooting - missing dependencies, checkpoint mismatch, headless rendering, and Gym/Gymnasium compatibility failures.
  • Root PPO API reference - constructor, select_action, save, and load details shared across sub-skills.

Validation commands

Safe checks for this sub-skill should avoid long rollouts unless the user explicitly has the environment packages, display, and checkpoint ready:

python scripts/evaluation_config_helper.py --help
python scripts/evaluation_config_helper.py --env-name CartPole-v1 --checkpoint-root PPO_preTrained --check-file
python -m py_compile scripts/evaluation_config_helper.py

A real episode rollout is optional and dependency-bound because the native test.py imports legacy gym and roboschool; do not treat a missing optional environment package as a failure of the helper or documentation.

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