Merge pull request #908 from j-svensmark:patch-1

PiperOrigin-RevId: 606257032
Change-Id: I505e062e6a6e568843e4f10fc91e07f2bfdea9e3

tf_agents/bandits/policies/linear_bandit_policy.py

@@ -107,7 +107,7 @@ def __init__(
       num_samples: list of number of samples per arm, unless the policy accepts
         per-arm features, in which case this is just the number of samples seen.
       time_step_spec: A `TimeStep` spec of the expected time_steps.
-      exploration_strategy: An Enum of type ExplortionStrategy. The strategy
+      exploration_strategy: An Enum of type ExplorationStrategy. The strategy
         used for choosing the actions to incorporate exploration. Currently
         supported strategies are `optimistic` and `sampling`.
       alpha: a float value used to scale the confidence intervals.