diff --git a/README.md b/README.md
index f2d3f0a9a..1a88055c3 100644
--- a/README.md
+++ b/README.md
@@ -40,7 +40,7 @@ For more information, you can refer to [PFRL's documentation](http://pfrl.readth
 
 ## Algorithms
 
-| Algorithm | Discrete Action | Continous Action | Recurrent Model | Batch Training | CPU Async Training | Pretrained models<sup>*</sup> |
+| Algorithm | Discrete Action | Continuous Action | Recurrent Model | Batch Training | CPU Async Training | Pretrained models<sup>*</sup> |
 |:----------|:---------------:|:----------------:|:---------------:|:--------------:|:------------------:|:------------------:|
 | DQN (including DoubleDQN etc.) | ✓ | ✓ (NAF) | ✓ | ✓ | x | ✓ |
 | Categorical DQN | ✓ | x | ✓ | ✓ | x | x |
diff --git a/pfrl/agents/trpo.py b/pfrl/agents/trpo.py
index 613b6258e..312185b95 100644
--- a/pfrl/agents/trpo.py
+++ b/pfrl/agents/trpo.py
@@ -687,7 +687,7 @@ def evaluate_current_policy():
             step_size *= 0.5
         else:
             self.logger.info(
-                "Line search coundn't find a good step size. The policy was not"
+                "Line search couldn't find a good step size. The policy was not"
                 " updated."
             )
             self.policy_step_size_record.append(0.0)
diff --git a/pfrl/experiments/prepare_output_dir.py b/pfrl/experiments/prepare_output_dir.py
index f82a95289..0c2387abc 100644
--- a/pfrl/experiments/prepare_output_dir.py
+++ b/pfrl/experiments/prepare_output_dir.py
@@ -23,7 +23,7 @@ def generate_exp_id(prefix=None, argv=sys.argv) -> str:
     checksum, git diff from HEAD and command line arguments.
 
     Returns:
-        A generated experiment id in string (str) which if avialable
+        A generated experiment id in string (str) which if available
         for directory name
 
     """
@@ -76,7 +76,7 @@ def prepare_output_dir(
     """Prepare a directory for outputting training results.
 
     An output directory, which ends with the current datetime string,
-    is created. Then the following infomation is saved into the directory:
+    is created. Then the following information is saved into the directory:
 
         args.txt: argument values and arbitrary parameters
         command.txt: command itself