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

Update simple.py

Browse Source
This commit is contained in:
Szymon Sidor
2017-07-12 23:42:36 +02:00
committed by GitHub
parent 04cd0dcf64
commit 2b1b437908
1 changed files with 1 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
baselines/deepq/simple.py
View File

@@ -89,7 +89,6 @@ def learn(env,
gamma=1.0,
target_network_update_freq=500,
prioritized_replay=False,
prioritized_importance_sampling=False,
prioritized_replay_alpha=0.6,
prioritized_replay_beta0=0.4,
prioritized_replay_beta_iters=None,
@@ -233,10 +232,7 @@ def learn(env,
else:
obses_t, actions, rewards, obses_tp1, dones = replay_buffer.sample(batch_size)
weights, batch_idxes = np.ones_like(rewards), None
if prioritized_importance_sampling:
td_errors = train(obses_t, actions, rewards, obses_tp1, dones, weights)
else:
td_errors = train(obses_t, actions, rewards, obses_tp1, dones, np.ones_like(rewards))
td_errors = train(obses_t, actions, rewards, obses_tp1, dones, weights)
if prioritized_replay:
new_priorities = np.abs(td_errors) + prioritized_replay_eps
replay_buffer.update_priorities(batch_idxes, new_priorities)