train Walk and tackle the memory leak issue.

train.sh

@@ -24,36 +24,14 @@ CPU_QUOTA="$((CORES * UTIL_PERCENT))%"
 MEMORY_MAX="${MEMORY_MAX:-0}"
 
 # ------------------------------
-# 训练运行参数（由 scripts/gyms/Walk.py 读取）
+# 精简运行参数（由 scripts/gyms/Walk.py 读取）
 # ------------------------------
-# 运行模式：train 或 test
+# 仅保留最常用开关，避免超长环境变量命令。
 GYM_CPU_MODE="${GYM_CPU_MODE:-train}"
-
-# 并行环境数量：越大通常吞吐越高，但也更容易触发 OOM 或连接不稳定。
-# 默认使用更稳妥的 12，确认稳定后再升到 16/20。
-GYM_CPU_N_ENVS="${GYM_CPU_N_ENVS:-12}"
-# 服务器预热时间（秒）：
-# 在批量拉起 rcssserver 后等待一段时间，再创建 SubprocVecEnv，
-# 可降低 ConnectionReset/EOFError 概率。
-GYM_CPU_SERVER_WARMUP_SEC="${GYM_CPU_SERVER_WARMUP_SEC:-10}"
-
-# 训练专用参数
-GYM_CPU_TRAIN_STEPS_PER_ENV="${GYM_CPU_TRAIN_STEPS_PER_ENV:-256}"
-GYM_CPU_TRAIN_BATCH_SIZE="${GYM_CPU_TRAIN_BATCH_SIZE:-512}"
-GYM_CPU_TRAIN_LR="${GYM_CPU_TRAIN_LR:-1e-4}"
-GYM_CPU_TRAIN_ENT_COEF="${GYM_CPU_TRAIN_ENT_COEF:-0.03}"
-GYM_CPU_TRAIN_CLIP_RANGE="${GYM_CPU_TRAIN_CLIP_RANGE:-0.13}"
-GYM_CPU_TRAIN_GAMMA="${GYM_CPU_TRAIN_GAMMA:-0.95}"
-GYM_CPU_TRAIN_EPOCHS="${GYM_CPU_TRAIN_EPOCHS:-5}"
+GYM_CPU_TRAIN_STAGE="${GYM_CPU_TRAIN_STAGE:-walk}"
 GYM_CPU_TRAIN_MODEL="${GYM_CPU_TRAIN_MODEL:-}"
-
-# 测试专用参数
 GYM_CPU_TEST_MODEL="${GYM_CPU_TEST_MODEL:-scripts/gyms/logs/Walk_R0_004/best_model.zip}"
 GYM_CPU_TEST_FOLDER="${GYM_CPU_TEST_FOLDER:-scripts/gyms/logs/Walk_R0_004/}"
-# 测试默认实时且显示画面：默认均为 0
-# 设为 1 表示关闭对应能力
-GYM_CPU_TEST_NO_RENDER="${GYM_CPU_TEST_NO_RENDER:-0}"
-GYM_CPU_TEST_NO_REALTIME="${GYM_CPU_TEST_NO_REALTIME:-0}"
 
 # Python 解释器选择策略：
 # 1) 优先使用你手动传入的 PYTHON_BIN
@@ -93,7 +71,7 @@ SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
 # 打印当前生效配置，方便排障和复现实验。
 echo "Starting training with limits: CPU=${CPU_QUOTA}, Memory=${MEMORY_MAX}"
 echo "Mode: ${GYM_CPU_MODE}"
-echo "Runtime knobs: GYM_CPU_N_ENVS=${GYM_CPU_N_ENVS}, GYM_CPU_SERVER_WARMUP_SEC=${GYM_CPU_SERVER_WARMUP_SEC}"
+echo "Run knobs: GYM_CPU_MODE=${GYM_CPU_MODE}, GYM_CPU_TRAIN_STAGE=${GYM_CPU_TRAIN_STAGE}"
 echo "Using Python: ${PYTHON_EXEC}"
 if [[ -n "${CONDA_DEFAULT_ENV:-}" ]]; then
 	echo "Detected conda env: ${CONDA_DEFAULT_ENV}"
@@ -118,19 +96,9 @@ systemd-run --user --scope \
 	"${SYSTEMD_PROPS[@]}" \
 	env \
 	GYM_CPU_MODE="${GYM_CPU_MODE}" \
-	GYM_CPU_N_ENVS="${GYM_CPU_N_ENVS}" \
-	GYM_CPU_SERVER_WARMUP_SEC="${GYM_CPU_SERVER_WARMUP_SEC}" \
-	GYM_CPU_TRAIN_STEPS_PER_ENV="${GYM_CPU_TRAIN_STEPS_PER_ENV}" \
-	GYM_CPU_TRAIN_BATCH_SIZE="${GYM_CPU_TRAIN_BATCH_SIZE}" \
-	GYM_CPU_TRAIN_LR="${GYM_CPU_TRAIN_LR}" \
-	GYM_CPU_TRAIN_ENT_COEF="${GYM_CPU_TRAIN_ENT_COEF}" \
-	GYM_CPU_TRAIN_CLIP_RANGE="${GYM_CPU_TRAIN_CLIP_RANGE}" \
-	GYM_CPU_TRAIN_GAMMA="${GYM_CPU_TRAIN_GAMMA}" \
-	GYM_CPU_TRAIN_EPOCHS="${GYM_CPU_TRAIN_EPOCHS}" \
+	GYM_CPU_TRAIN_STAGE="${GYM_CPU_TRAIN_STAGE}" \
 	GYM_CPU_TRAIN_MODEL="${GYM_CPU_TRAIN_MODEL}" \
 	GYM_CPU_TEST_MODEL="${GYM_CPU_TEST_MODEL}" \
 	GYM_CPU_TEST_FOLDER="${GYM_CPU_TEST_FOLDER}" \
-	GYM_CPU_TEST_NO_RENDER="${GYM_CPU_TEST_NO_RENDER}" \
-	GYM_CPU_TEST_NO_REALTIME="${GYM_CPU_TEST_NO_REALTIME}" \
 	"${PYTHON_EXEC}" "-m" "scripts.gyms.Walk"