[go: nahoru, domu]

Skip to content

Commit

Permalink
Fix typos in PPOAgent docstrings
Browse files Browse the repository at this point in the history
  • Loading branch information
seungjaeryanlee committed Aug 3, 2019
1 parent a56ebeb commit 58fc329
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions tf_agents/agents/ppo/ppo_agent.py
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,7 @@ def __init__(self,
value_predictions)
normalize_rewards: If true, keeps moving variance of rewards and
normalizes incoming rewards.
reward_norm_clipping: Value above an below to clip normalized reward.
reward_norm_clipping: Value above and below to clip normalized reward.
normalize_observations: If true, keeps moving mean and variance of
observations and normalizes incoming observations.
log_prob_clipping: +/- value for clipping log probs to prevent inf / NaN
Expand Down Expand Up @@ -394,7 +394,7 @@ def compute_return_and_advantage(self, next_time_steps, value_preds):
Args:
next_time_steps: batched tensor of TimeStep tuples after action is taken.
value_preds: Batched value predction tensor. Should have one more entry in
value_preds: Batched value prediction tensor. Should have one more entry in
time index than time_steps, with the final value corresponding to the
value prediction of the final state.
Expand Down

0 comments on commit 58fc329

Please sign in to comment.