make tests use single-threaded session for determinism of KfacOptimizer (#298)

* make tests use single-threaded session for determinism of KfacOptimizer

* updated comment in kfac.py

* remove unused sess_config

baselines/acktr/acktr.py

@@ -90,7 +90,7 @@ class Model(object):
         self.initial_state = step_model.initial_state
         tf.global_variables_initializer().run(session=sess)
 
-def learn(network, env, seed, total_timesteps=int(40e6), gamma=0.99, log_interval=1, nprocs=32, nsteps=20,
+def learn(network, env, seed, total_timesteps=int(40e6), gamma=0.99, log_interval=100, nprocs=32, nsteps=20,
                  ent_coef=0.01, vf_coef=0.5, vf_fisher_coef=1.0, lr=0.25, max_grad_norm=0.5,
                  kfac_clip=0.001, save_interval=None, lrschedule='linear', load_path=None, is_async=True, **network_kwargs):
     set_global_seeds(seed)

baselines/acktr/kfac.py

@@ -11,7 +11,7 @@ KFAC_DEBUG = False
 
 
 class KfacOptimizer():
-
+    # note that KfacOptimizer will be truly synchronous (and thus deterministic) only if a single-threaded session is used
     def __init__(self, learning_rate=0.01, momentum=0.9, clip_kl=0.01, kfac_update=2, stats_accum_iter=60, full_stats_init=False, cold_iter=100, cold_lr=None, is_async=False, async_stats=False, epsilon=1e-2, stats_decay=0.95, blockdiag_bias=False, channel_fac=False, factored_damping=False, approxT2=False, use_float64=False, weight_decay_dict={},max_grad_norm=0.5):
         self.max_grad_norm = max_grad_norm
         self._lr = learning_rate

baselines/common/tests/util.py

@@ -5,6 +5,12 @@ from baselines.common.vec_env.dummy_vec_env import DummyVecEnv
 N_TRIALS = 10000
 N_EPISODES = 100
 
+_sess_config = tf.ConfigProto(
+    allow_soft_placement=True,
+    intra_op_parallelism_threads=1,
+    inter_op_parallelism_threads=1
+)
+
 def simple_test(env_fn, learn_fn, min_reward_fraction, n_trials=N_TRIALS):
     def seeded_env_fn():
         env = env_fn()
@@ -13,7 +19,7 @@ def simple_test(env_fn, learn_fn, min_reward_fraction, n_trials=N_TRIALS):
 
     np.random.seed(0)
     env = DummyVecEnv([seeded_env_fn])
-    with tf.Graph().as_default(), tf.Session(config=tf.ConfigProto(allow_soft_placement=True)).as_default():
+    with tf.Graph().as_default(), tf.Session(config=_sess_config).as_default():
         tf.set_random_seed(0)
         model = learn_fn(env)
         sum_rew = 0
@@ -34,7 +40,7 @@ def simple_test(env_fn, learn_fn, min_reward_fraction, n_trials=N_TRIALS):
 
 def reward_per_episode_test(env_fn, learn_fn, min_avg_reward, n_trials=N_EPISODES):
     env = DummyVecEnv([env_fn])
-    with tf.Graph().as_default(), tf.Session(config=tf.ConfigProto(allow_soft_placement=True)).as_default():
+    with tf.Graph().as_default(), tf.Session(config=_sess_config).as_default():
         model = learn_fn(env)
         N_TRIALS = 100
         observations, actions, rewards = rollout(env, model, N_TRIALS)