gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ppo2: use time.perf_counter() instead of time.time() for time measurement (#847)

Browse Source
This commit is contained in:
zlsh80826
2019-04-02 06:37:32 +08:00
committed by pzhokhov
parent 897fa31548
commit c02b575f01
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
baselines/ppo2/ppo2.py
View File

@@ -119,13 +119,13 @@ def learn(*, network, env, total_timesteps, eval_env = None, seed=None, nsteps=2
eval_epinfobuf = deque(maxlen=100)
# Start total timer
tfirststart = time.time()
tfirststart = time.perf_counter()
nupdates = total_timesteps//nbatch
for update in range(1, nupdates+1):
assert nbatch % nminibatches == 0
# Start timer
tstart = time.time()
tstart = time.perf_counter()
frac = 1.0 - (update - 1.0) / nupdates
# Calculate the learning rate
lrnow = lr(frac)
@@ -173,7 +173,7 @@ def learn(*, network, env, total_timesteps, eval_env = None, seed=None, nsteps=2
# Feedforward --> get losses --> update
lossvals = np.mean(mblossvals, axis=0)
# End timer
tnow = time.time()
tnow = time.perf_counter()
# Calculate the fps (frame per second)
fps = int(nbatch / (tnow - tstart))
if update % log_interval == 0 or update == 1: