fixes to readme and baselines/run.py (#80)

* fixes to readme and baselines/run.py

* polish installation section of baselines README

* polish installation section of baselines README

README.md

@@ -38,20 +38,27 @@ More thorough tutorial on virtualenvs and options can be found [here](https://vi
 
 
 ## Installation
-Clone the repo and cd into it:
+- Clone the repo and cd into it:
-```bash
+    ```bash
-git clone https://github.com/openai/baselines.git
+    git clone https://github.com/openai/baselines.git
-cd baselines
+    cd baselines
-```
+    ```
-If using virtualenv, create a new virtualenv and activate it
+- If you don't have TensorFlow installed already, install your favourite flavor of TensorFlow. In most cases, 
-```bash
+    ```bash 
-virtualenv env --python=python3
+    pip install tensorflow-gpu # if you have a CUDA-compatible gpu and proper drivers
-. env/bin/activate
+    ```
-```
+    or 
-Install baselines package
+    ```bash
-```bash
+    pip install tensorflow
-pip install -e .
+    ```
-```
+    should be sufficient. Refer to [TensorFlow installation guide](https://www.tensorflow.org/install/)
+    for more details. 
+
+- Install baselines package
+    ```bash
+    pip install -e .
+    ```
+
 ### MuJoCo
 Some of the baselines examples use [MuJoCo](http://www.mujoco.org) (multi-joint dynamics in contact) physics simulator, which is proprietary and requires binaries and a license (temporary 30-day license can be obtained from [www.mujoco.org](http://www.mujoco.org)). Instructions on setting up MuJoCo can be found [here](https://github.com/openai/mujoco-py)
 
@@ -103,6 +110,13 @@ python -m baselines.run --alg=ppo2 --env=PongNoFrameskip-v4 --num_timesteps=0 --
 *NOTE:* At the moment Mujoco training uses VecNormalize wrapper for the environment which is not being saved correctly; so loading the models trained on Mujoco will not work well if the environment is recreated. If necessary, you can work around that by replacing RunningMeanStd by TfRunningMeanStd in [baselines/common/vec_env/vec_normalize.py](baselines/common/vec_env/vec_normalize.py#L12). This way, mean and std of environment normalizing wrapper will be saved in tensorflow variables and included in the model file; however, training is slower that way - hence not including it by default
 
 
+## Using baselines with TensorBoard
+Baselines logger can save data in the TensorBoard format. To do so, set environment variables `OPENAI_LOG_FORMAT` and `OPENAI_LOGDIR`:
+```bash
+export OPENAI_LOG_FORMAT='stdout,log,csv,tensorboard' # formats are comma-separated, but for tensorboard you only really need the last one
+export OPENAI_LOGDIR=path/to/tensorboard/data
+```
+
 ## Subpackages
 
 - [A2C](baselines/a2c)

baselines/run.py

@@ -13,7 +13,6 @@ from baselines import bench, logger
 from importlib import import_module
 
 from baselines.common.vec_env.vec_normalize import VecNormalize
-from baselines.common.vec_env.dummy_vec_env import DummyVecEnv
 from baselines.common import atari_wrappers, retro_wrappers
 
 try:
@@ -92,19 +91,8 @@ def build_env(args):
     seed = args.seed
 
     env_type, env_id = get_env_type(args.env)
-    if env_type == 'mujoco':
-        get_session(tf.ConfigProto(allow_soft_placement=True,
-                                   intra_op_parallelism_threads=1,
-                                   inter_op_parallelism_threads=1))
 
-        if args.num_env:
+    if env_type == 'atari':
-            env = make_vec_env(env_id, env_type, nenv, seed, reward_scale=args.reward_scale)
-        else:
-            env = make_vec_env(env_id, env_type, 1, seed, reward_scale=args.reward_scale)
-
-        env = VecNormalize(env)
-
-    elif env_type == 'atari':
         if alg == 'acer':
             env = make_vec_env(env_id, env_type, nenv, seed)
         elif alg == 'deepq':
@@ -132,17 +120,15 @@ def build_env(args):
         env = bench.Monitor(env, logger.get_dir())
         env = retro_wrappers.wrap_deepmind_retro(env)
 
-    elif env_type == 'classic_control':
-        def make_env():
-            e = gym.make(env_id)
-            e = bench.Monitor(e, logger.get_dir(), allow_early_resets=True)
-            e.seed(seed)
-            return e
-
-        env = DummyVecEnv([make_env])
-
     else: 
-        raise ValueError('Unknown env_type {}'.format(env_type))
+       get_session(tf.ConfigProto(allow_soft_placement=True,
+                                   intra_op_parallelism_threads=1,
+                                   inter_op_parallelism_threads=1))
+
+       env = make_vec_env(env_id, env_type, args.num_env or 1, seed, reward_scale=args.reward_scale)
+
+       if env_type == 'mujoco':
+           env = VecNormalize(env) 
 
     return env
 
@@ -163,10 +149,10 @@ def get_env_type(env_id):
 
 
 def get_default_network(env_type):
-    if env_type == 'mujoco' or env_type == 'classic_control':
-        return 'mlp'
     if env_type == 'atari':
         return 'cnn'
+    else:
+        return 'mlp'
 
     raise ValueError('Unknown env_type {}'.format(env_type))