update to 2.2RC (PaddlePaddle#3997)

* update to 2.2 * add docs-build.sh * update to 2.2 * update to 2.2 * update release note
huangjun12 · Oct 22, 2021 · afc4864 · afc4864
1 parent f0d0e50
commit afc4864
Show file tree

Hide file tree

Showing 114 changed files with 5,105 additions and 4,288 deletions.
diff --git a/docs-build.sh b/docs-build.sh
@@ -0,0 +1,125 @@
+#!/bin/bash
+
+# renwei 先打印下参数列表
+# echo $@
+
+SELFNAME=$0 
+SHORT=f:p:w:hx:
+LONG=docs-dir:,paddle-dir:,paddle-whl:,https-proxy:
+
+OPTIND=1
+
+show_help() {
+  cat <<HELP_HELP_HELP
+$SELFNAME -f <docs-dir> [-p <paddle-dir>]
+$SELFNAME -f <docs-dir> [-w <paddle-whl>]
+$SELFNAME -f <docs-dir>
+Options:
+    -f docs Project Dir
+    -p Paddle Project Dir
+    -w Paddle whl, local filename or http(s) file
+    -h Show help
+    -x Set https_proxy
+HELP_HELP_HELP
+}
+
+while getopts $SHORT opt; do
+    case "$opt" in
+        f)
+            FLUIDDOC_DIR=$OPTARG
+            ;;
+        p)
+            PADDLE_DIR=$OPTARG
+            ;;
+        w)
+            PADDLE_WHL=$OPTARG
+            ;;
+        x)
+            https_proxy=$OPTARG
+            ;;
+        h)
+            show_help
+            exit 0
+            ;;
+    esac
+done
+
+
+if [ "$FLUIDDOC_DIR" = '' ] ; then
+    echo "-f docs-dir must be specified."
+    exit 5
+fi
+
+
+VERSIONSTR=${VERSIONSTR:=develop}
+
+SPHINX_DOCKERIMAGE=registry.baidubce.com/paddleopen/fluiddoc-sphinx:20210610-py38
+PADDLEDEV_DOCKERIMAGE=registry.baidubce.com/paddlepaddle/paddle:latest-dev-cuda10.1-cudnn7-gcc82
+
+
+if [ "$PADDLE_WHL" = '' ] && [ "$PADDLE_DIR" = '' ] ; then
+  docker run -it --rm --entrypoint=bash \
+    -e VERSIONSTR=${VERSIONSTR} \
+    -v ${FLUIDDOC_DIR}:/FluidDoc \
+    -v ${FLUIDDOC_DIR}/output:/docs \
+    -v ${HOME}/.doctrees:/var/doctrees \
+    ${SPHINX_DOCKERIMAGE} \
+    /root/fluiddoc-gendoc.sh
+  exit 0
+fi
+
+if ! [ "$PADDLE_WHL" = '' ]; then
+  if [[ ${PADDLE_WHL} = http* ]]; then
+    docker run -it --rm --entrypoint=bash \
+      -e VERSIONSTR=${VERSIONSTR} \
+      -e https_proxy=${https_proxy} \
+      -v ${FLUIDDOC_DIR}:/FluidDoc \
+      -v ${FLUIDDOC_DIR}/output:/docs \
+      -v ${HOME}/.doctrees:/var/doctrees \
+      ${SPHINX_DOCKERIMAGE} \
+      /root/fluiddoc-gendoc.sh ${PADDLE_WHL}
+  else
+    WHL_DIR=$(dirname $PADDLE_WHL)
+    WHL_FN=$(basename $PADDLE_WHL)
+    docker run -it --rm --entrypoint=bash \
+      -e VERSIONSTR=${VERSIONSTR} \
+      -e https_proxy=${https_proxy} \
+      -v ${FLUIDDOC_DIR}:/FluidDoc \
+      -v ${FLUIDDOC_DIR}/output:/docs \
+      -v ${HOME}/.doctrees:/var/doctrees \
+      -v ${WHL_DIR}:/whls \
+      ${SPHINX_DOCKERIMAGE} \
+      /root/fluiddoc-gendoc.sh /whls/${WHL_FN}
+  fi
+  exit 0
+fi
+
+if ! [ "$PADDLE_DIR" = '' ]; then
+  docker run -it --rm \
+    -e PADDLE_VERSION=${VERSIONSTR} \
+    -e https_proxy=${https_proxy} \
+    -v ${PADDLE_DIR}:/paddle \
+    -v ${HOME}/.cache:/root/.cache \
+    -v ${PADDLE_DIR}/build/python/dist:/paddle/build/python/dist \
+    --workdir=/paddle/build \
+    --entrypoint=bash \
+    ${PADDLEDEV_DOCKERIMAGE} \
+    -c 'cmake .. -DPY_VERSION=3.8 -DWITH_GPU=OFF -DWITH_TESTING=OFF -DCMAKE_BUILD_TYPE=Release && make -j$(nproc)'
+
+  if ! [ "${AUTOFINDWHL}" = "off" ] ; then
+    WHL_FULLFN=$(find ${PADDLE_DIR}/build/python/dist -type f -name 'paddlepaddle*cp38*linux_x86_64.whl' -printf "%T+\t%p\n" | sort -r | head -n 1| cut -f 2)
+    WHL_FN=$(basename ${WHL_FULLFN:-paddle.whl})
+  fi
+
+  docker run -it --rm --entrypoint=bash \
+    -e VERSIONSTR=${VERSIONSTR} \
+    -e https_proxy=${https_proxy} \
+    -v ${FLUIDDOC_DIR}/:/FluidDoc \
+    -v ${FLUIDDOC_DIR}/output:/docs \
+    -v ${HOME}/.doctrees:/var/doctrees \
+    -v ${PADDLE_DIR}/build/python/dist:/whls \
+    ${SPHINX_DOCKERIMAGE} \
+    /root/fluiddoc-gendoc.sh /whls/${WHL_FN}
+  exit 0
+fi
+
diff --git a/docs/api/index_cn.rst b/docs/api/index_cn.rst
@@ -23,6 +23,10 @@ API 文档
 +-------------------------------+-------------------------------------------------------+
 | paddle.device                 | 设备管理相关API，包括 set_device, get_device 等。     |
 +-------------------------------+-------------------------------------------------------+
+| paddle.linalg                 | 线性代数相关API，包括 det, svd 等。                   |
++-------------------------------+-------------------------------------------------------+
+| paddle.fft                    | 快速傅里叶变换的相关API，包括 fft, fft2 等。          |
++-------------------------------+-------------------------------------------------------+
 | paddle.amp                    | 自动混合精度策略，包括 auto_cast 、                   |
 |                               | GradScaler 等。                                       |
 +-------------------------------+-------------------------------------------------------+
@@ -31,9 +35,9 @@ API 文档
 | paddle.callbacks              | 日志回调类，包括 ModelCheckpoint 、                   |
 |                               | ProgBarLogger 等。                                    |
 +-------------------------------+-------------------------------------------------------+
-| paddle.distributed            | 分布式相关基础API                                     |
+| paddle.distributed            | 分布式相关基础API。                                   |
 +-------------------------------+-------------------------------------------------------+
-| paddle.distributed.fleet      | 分布式相关高层API                                     |
+| paddle.distributed.fleet      | 分布式相关高层API。                                   |
 +-------------------------------+-------------------------------------------------------+
 | paddle.hub                    | 模型拓展相关的API，包括 list、load、help 等。         |
 +-------------------------------+-------------------------------------------------------+

diff --git a/docs/api/index_en.rst b/docs/api/index_en.rst
@@ -26,6 +26,11 @@ In this version, PaddlePaddle has made many optimizations to the APIs. You can r
 | paddle.device                 | Device management related APIs, such as set_device,   |
 |                               | get_device, etc.                                      |
 +-------------------------------+-------------------------------------------------------+
+| paddle.linalg                 | Linear algebra related APIs, such as det, svd, etc.   |    
++-------------------------------+-------------------------------------------------------+
+| paddle.fft                    | Fast Fourier Transform related APIs, such as          |
+|                               | fft, fft2, etc.                                       |
++-------------------------------+-------------------------------------------------------+
 | paddle.amp                    | Paddle automatic mixed precision strategy, including  | 
 |                               | auto_cast, GradScaler, etc.                           |
 +-------------------------------+-------------------------------------------------------+

diff --git a/docs/practices/Actor_Critic_Method/Actor_Critic_Method.ipynb b/docs/practices/Actor_Critic_Method/Actor_Critic_Method.ipynb
@@ -8,7 +8,7 @@
    "source": [
     "# **强化学习——Actor Critic Method**\n",
     "**作者：** [EastSmith](https://github.com/EastSmith)<br>\n",
-    "**日期：** 2021.05 <br>\n",
+    "**日期：** 2021.10 <br>\n",
     "**摘要：** 展示 `CartPole-V0` 环境中 `Actor-Critic` 方法的一个实现。"
    ]
   },
@@ -39,7 +39,7 @@
    },
    "source": [
     "## **二、环境配置**\n",
-    "本教程基于Paddle 2.1 编写，如果你的环境不是本版本，请先参考官网[安装](https://www.paddlepaddle.org.cn/install/quick) Paddle 2.1 。"
+    "本教程基于Paddle 2.2.0-rc0 编写，如果你的环境不是本版本，请先参考官网[安装](https://www.paddlepaddle.org.cn/install/quick) Paddle 2.2.0-rc0 。"
    ]
   },
   {
@@ -53,7 +53,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.1.0\n"
+      "2.2.0-rc0\n"
      ]
     }
    ],
@@ -149,31 +149,13 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Iteration: 0, Score: 32\n",
-      "Iteration: 10, Score: 43\n",
-      "Iteration: 20, Score: 11\n",
-      "Iteration: 30, Score: 18\n",
-      "Iteration: 40, Score: 39\n",
-      "Iteration: 50, Score: 18\n",
-      "Iteration: 60, Score: 104\n",
-      "Iteration: 70, Score: 82\n",
-      "Iteration: 80, Score: 199\n",
-      "Iteration: 90, Score: 199\n",
-      "Iteration: 100, Score: 199\n"
-     ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-3-c23b84fbafb3>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     84\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m         \u001b[0mcritic\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCritic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstate_size\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maction_size\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 86\u001b[0;31m     \u001b[0mtrainIters\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mactor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcritic\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mn_iters\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m201\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;32m<ipython-input-3-c23b84fbafb3>\u001b[0m in \u001b[0;36mtrainIters\u001b[0;34m(actor, critic, n_iters)\u001b[0m\n\u001b[1;32m     46\u001b[0m         \u001b[0mnext_state\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpaddle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnext_state\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"float32\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mplace\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdevice\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     47\u001b[0m         \u001b[0mnext_value\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcritic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnext_state\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 48\u001b[0;31m         \u001b[0mreturns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompute_returns\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnext_value\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrewards\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmasks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     49\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     50\u001b[0m         \u001b[0mlog_probs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpaddle\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconcat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlog_probs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m<ipython-input-3-c23b84fbafb3>\u001b[0m in \u001b[0;36mcompute_returns\u001b[0;34m(next_value, rewards, masks, gamma)\u001b[0m\n\u001b[1;32m      3\u001b[0m     \u001b[0mreturns\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m     \u001b[0;32mfor\u001b[0m \u001b[0mstep\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mreversed\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrewards\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 5\u001b[0;31m         \u001b[0mR\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrewards\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mgamma\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mR\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mmasks\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mstep\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      6\u001b[0m         \u001b[0mreturns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minsert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mR\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mreturns\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/math_op_patch.py\u001b[0m in \u001b[0;36m__impl__\u001b[0;34m(self, other_var)\u001b[0m\n\u001b[1;32m    248\u001b[0m             \u001b[0maxis\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    249\u001b[0m             \u001b[0mmath_op\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mops\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mop_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 250\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mmath_op\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mother_var\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'axis'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    251\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    252\u001b[0m         \u001b[0mcomment\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mOpProtoHolder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_op_proto\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop_type\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcomment\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
+      "Iteration: 0, Score: 19\n",
+      "Iteration: 10, Score: 18\n",
+      "Iteration: 20, Score: 16\n",
+      "Iteration: 30, Score: 29\n",
+      "Iteration: 40, Score: 16\n",
+      "Iteration: 50, Score: 52\n",
+      "Iteration: 60, Score: 53\n"
      ]
     }
    ],
@@ -297,7 +279,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "PaddlePaddle 2.0.0b0 (Python 3.5)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "py35-paddle1.2.0"
   },

diff --git a/docs/practices/Advantage Actor-Critic(A2C)/Advantage Actor-Critic(A2C).ipynb b/docs/practices/Advantage Actor-Critic(A2C)/Advantage Actor-Critic(A2C).ipynb
@@ -9,7 +9,7 @@
     "#  **强化学习——Advantage Actor-Critic(A2C)**\n",
     "**作者：**:[EastSmith](https://github.com/EastSmith)\n",
     "\n",
-    "**日期：** 2021.05 \n",
+    "**日期：** 2021.10\n",
     "\n",
     "**AI Studio项目**：[点击体验](https://aistudio.baidu.com/aistudio/projectdetail/1766508)\n",
     "## **一、介绍**\n",
@@ -57,12 +57,12 @@
    },
    "source": [
     "## **二、环境配置**\n",
-    "本教程基于Paddle 2.1 编写，如果您的环境不是本版本，请先参考官网[安装](https://www.paddlepaddle.org.cn/install/quick) Paddle 2.1 。"
+    "本教程基于Paddle 2.2.0-rc0 编写，如果您的环境不是本版本，请先参考官网[安装](https://www.paddlepaddle.org.cn/install/quick) Paddle 2.2.0-rc0。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {
     "collapsed": false
    },
@@ -100,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {
     "collapsed": false
    },
@@ -266,7 +266,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {
     "collapsed": false
    },
@@ -307,13 +307,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
-    "\r\n",
     "class ActorCritic(nn.Layer):\r\n",
     "    def __init__(self, num_inputs, num_outputs, hidden_size, std=0.0):\r\n",
     "        super(ActorCritic, self).__init__()\r\n",
@@ -381,13 +380,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
-    "\r\n",
     "num_inputs  = envs.observation_space.shape[0]\r\n",
     "num_outputs = envs.action_space.n\r\n",
     "\r\n",
@@ -402,8 +400,7 @@
     "if os.path.exists(save_model_path):\r\n",
     "    model_state_dict  = paddle.load(save_model_path)\r\n",
     "    model.set_state_dict(model_state_dict )\r\n",
-    "    print(' Model loaded')\r\n",
-    "\r\n"
+    "    print(' Model loaded')"
    ]
   },
   {
@@ -418,23 +415,55 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {
     "collapsed": false
    },
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/math_op_patch.py:248: UserWarning: The dtype of left and right variables are not the same, left dtype is paddle.float32, but right dtype is paddle.int64, the right dtype will convert to paddle.float32\n",
+      "  format(lhs_dtype, rhs_dtype, lhs_dtype))\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "frame 19300. reward: 200.0\n",
-      "frame 19400. reward: 200.0\n",
-      "frame 19500. reward: 200.0\n",
-      "frame 19600. reward: 200.0\n",
-      "frame 19700. reward: 200.0\n",
-      "frame 19800. reward: 200.0\n",
-      "frame 19900. reward: 200.0\n",
-      "frame 20000. reward: 200.0\n"
+      "frame 100. reward: 25.5\n",
+      "frame 200. reward: 35.0\n",
+      "frame 300. reward: 18.0\n",
+      "frame 400. reward: 11.5\n",
+      "frame 500. reward: 13.0\n",
+      "frame 600. reward: 12.0\n",
+      "frame 700. reward: 20.5\n",
+      "frame 800. reward: 22.0\n",
+      "frame 900. reward: 18.5\n",
+      "frame 1000. reward: 13.0\n",
+      "frame 1100. reward: 9.0\n",
+      "frame 1200. reward: 10.0\n",
+      "frame 1300. reward: 11.5\n",
+      "frame 1400. reward: 9.5\n",
+      "frame 1500. reward: 10.0\n",
+      "frame 1600. reward: 10.0\n",
+      "frame 1700. reward: 9.0\n",
+      "frame 1800. reward: 10.0\n",
+      "frame 1900. reward: 9.5\n",
+      "frame 2000. reward: 9.0\n",
+      "frame 2100. reward: 10.0\n",
+      "frame 2200. reward: 9.5\n",
+      "frame 2300. reward: 10.5\n",
+      "frame 2400. reward: 8.5\n",
+      "frame 2500. reward: 9.5\n",
+      "frame 2600. reward: 9.5\n",
+      "frame 2700. reward: 9.0\n",
+      "frame 2800. reward: 9.5\n",
+      "frame 2900. reward: 9.0\n",
+      "frame 3000. reward: 9.5\n",
+      "frame 3100. reward: 12.0\n",
+      "frame 3200. reward: 9.0\n"
      ]
     }
    ],
@@ -571,7 +600,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "PaddlePaddle 2.0.0b0 (Python 3.5)",
+   "display_name": "Python 3",
    "language": "python",
    "name": "py35-paddle1.2.0"
   },