Train 代码测试

AI 智能社区

作者仓库星标 1,155
许可证 BSD-2-Clause
作者仓库 LearningHumanoidWalking

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

原文结构

Command Template：原文以此为独立章节。
Available Environments：Name · Description cartpole · Cartpole swing-up (simplest, good for testing) h1 · Unitree H1 standing task
Hyperparameters (defaults)：Flag · Default · Description --n-itr · 20000 · Training iterations --lr · 1e-4 · Learning rate

适用与边界

当前原文没有单列适用场景。
当前原文没有单列不适用场景或限制。

原文中的明确线索

要点：「Parse the user's request from $ARGUMENTS and construct a training command.」、「1. Determine the environment name from the user's request.」、「Suggest these defaults when the user trains cartpole, but let them override.」
文件与命令：$ARGUMENTS、cartpole、jvrcwalk、jvrcstep、--n-itr、--lr、--gamma、--std-dev

流狐整理：以上内容来自当前 SKILL.md 的章节与原词；未补写作者没有声明的工具、兼容性或能力。

/train — Launch a PPO Training Run

Parse the user's request from $ARGUMENTS and construct a training command.

Command Template

RAY_ADDRESS= uv run python run_experiment.py train --env <ENV> --logdir <LOGDIR> [OPTIONS...]

Available Environments

Name	Description
`cartpole`	Cartpole swing-up (simplest, good for testing)
`h1`	Unitree H1 standing task
`jvrc_walk`	JVRC humanoid basic walking
`jvrc_step`	JVRC humanoid stepping with planned footsteps

Hyperparameters (defaults)

Flag	Default	Description
`--n-itr`	20000	Training iterations
`--lr`	1e-4	Learning rate
`--gamma`	0.99	Discount factor
`--std-dev`	0.223	Action noise
`--learn-std`	off	Learn action noise (flag)
`--entropy-coeff`	0.0	Entropy regularization
`--clip`	0.2	PPO clipping
`--minibatch-size`	64	Minibatch size
`--epochs`	3	Optimization epochs per update
`--num-procs`	12	Parallel workers
`--num-envs-per-worker`	1	Vectorized envs per worker
`--max-grad-norm`	0.05	Gradient clipping
`--max-traj-len`	400	Episode horizon
`--eval-freq`	100	Eval every N iterations
`--seed`	None	Random seed
`--device`	auto	Training device (auto/cpu/cuda)
`--no-mirror`	off	Disable symmetry wrapper (flag)
`--recurrent`	off	Use LSTM policy (flag)
`--continued`	None	Path to pretrained weights

Instructions

Determine the environment name from the user's request. If ambiguous, ask.
Use --logdir /tmp/training_runs unless the user specifies a different path.
Only include flags that differ from defaults — keep the command clean.
Show the user the full command you're about to run.
Run the command in the background using run_in_background: true on the Bash tool. Set a generous timeout (600000ms).
After launching, tell the user the logdir path and how to check progress (you can tail the output using the task ID).
If the user asks to check on training, use TaskOutput with block: false to check the latest output.

Cartpole-Specific Defaults

For cartpole, these settings are known to work well with the current defaults (--lr 3e-4 --max-grad-norm 0.5 --lam 0.95 --gamma 0.99):

--minibatch-size 256
--std-dev 0.15 --learn-std --entropy-coeff 0.01
--max-traj-len 500 --n-itr 500 --num-procs 12
--no-mirror (cartpole has no body symmetry)

Suggest these defaults when the user trains cartpole, but let them override.

流狐档案作者与许可取自来源；运行、权限和网络为流狐检测或估算

流狐分类: AI 智能
作者声明 Agent: 未找到明确声明；不据此推断已兼容或已测试
静态检查: 94 / 100 · 启发式扫描，不代表运行安全
作者 / 版本 / 许可: @rohanpsingh · BSD-2-Clause
流狐 Token 估算: 低消耗
流狐接入估算: 即装即用
是否需要外部 API Key: 未发现要求
检测到的系统要求: 未声明
底层运行要求: Python
检测到的文件与系统行为: 只读
允许写入 / 修改
检测到的网络行为: 仅限本地
安装命令数: 无（仅作为资料）

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 train.preview

作者没有在当前 SKILL.md 中定义固定输出样例。

SKILL.md SKILL.md

# /train — Launch a PPO Training Run

Parse the user's request from `$ARGUMENTS` and construct a training command.

## Command Template

```
RAY_ADDRESS= uv run python run_experiment.py train --env <ENV> --logdir <LOGDIR> [OPTIONS...]
```

## Available Environments

| Name | Description |
|------|-------------|
| `cartpole` | Cartpole swing-up (simplest, good for testing) |
| `h1` | Unitree H1 standing task |
| `jvrc_walk` | JVRC humanoid basic walking |
| `jvrc_step` | JVRC humanoid stepping with planned footsteps |

## Hyperparameters (defaults)

| Flag | Default | Description |
|------|---------|-------------|
| `--n-itr` | 20000 | Training iterations |
| `--lr` | 1e-4 | Learning rate |
| `--gamma` | 0.99 | Discount factor |
| `--std-dev` | 0.223 | Action noise |
| `--learn-std` | off | Learn action noise (flag) |
| `--entropy-coeff` | 0.0 | Entropy regularization |
| `--clip` | 0.2 | PPO clipping |
| `--minibatch-size` | 64 | Minibatch size |
| `--epochs` | 3 | Optimization epochs per update |
| `--num-procs` | 12 | Parallel workers |
| `--num-envs-per-worker` | 1 | Vectorized envs per worker |
| `--max-grad-norm` | 0.05 | Gradient clipping |
| `--max-traj-len` | 400 | Episode horizon |
| `--eval-freq` | 100 | Eval every N iterations |
| `--seed` | None | Random seed |
| `--device` | auto | Training device (auto/cpu/cuda) |
| `--no-mirror` | off | Disable symmetry wrapper (flag) |
| `--recurrent` | off | Use LSTM policy (flag) |
| `--continued` | None | Path to pretrained weights |

## Instructions

1. Determine the environment name from the user's request. If ambiguous, ask.
2. Use `--logdir /tmp/training_runs` unless the user specifies a different path.
3. Only include flags that differ from defaults — keep the command clean.

…

证据边界与执行链路

作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。

章节    -> Command Template → Available Environments → Hyperparameters (defaults) → Instructions → Cartpole-Specific Defaults
要点    -> Parse the user's request from $ARGUMENTS and construct a training command. · 1. Determine the environment name from the user's request. · Suggest these defaults when the user trains cartpole, but let them override.
文件/命令 -> $ARGUMENTS · cartpole · jvrcwalk · jvrcstep · --n-itr · --lr · --gamma · --std-dev
内容 SHA-256 -> 67a84e6e2fb7