diff --git a/NEWS.md b/NEWS.md
index 2d6162f83..7ff7d6fd3 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -185,6 +185,10 @@
 
 ### ReinforcementLearningCore.jl
 
+#### v0.10.1
+
+- Fix hook issue with 'extra' call; always run `push!` at end of episode, regardless of whether stopped or terminated
+
 #### v0.10.0
 
 - Transition to `RLCore.forward`, `RLBase.act!`, `RLBase.plan!` and `Base.push!` syntax instead of functional objects for hooks, policies and environments
diff --git a/src/ReinforcementLearningCore/Project.toml b/src/ReinforcementLearningCore/Project.toml
index 1d85301b0..b6743add3 100644
--- a/src/ReinforcementLearningCore/Project.toml
+++ b/src/ReinforcementLearningCore/Project.toml
@@ -1,6 +1,6 @@
 name = "ReinforcementLearningCore"
 uuid = "de1b191a-4ae0-4afa-a27b-92d07f46b2d6"
-version = "0.10.0"
+version = "0.10.1"
 
 [deps]
 AbstractTrees = "1520ce14-60c1-5f80-bbc7-55ef81b5835c"
diff --git a/src/ReinforcementLearningCore/src/core/hooks.jl b/src/ReinforcementLearningCore/src/core/hooks.jl
index 176ad7f2b..c75531470 100644
--- a/src/ReinforcementLearningCore/src/core/hooks.jl
+++ b/src/ReinforcementLearningCore/src/core/hooks.jl
@@ -90,9 +90,9 @@ Base.getindex(h::StepsPerEpisode) = h.steps
 
 Base.push!(hook::StepsPerEpisode, ::PostActStage, args...) = hook.count += 1
 
-Base.push!(hook::StepsPerEpisode, stage::Union{PostEpisodeStage,PostExperimentStage}, agent, env, ::Symbol) = Base.push!(hook, stage, agent, env)
+Base.push!(hook::StepsPerEpisode, stage::PostEpisodeStage, agent, env, ::Symbol) = Base.push!(hook, stage, agent, env)
 
-function Base.push!(hook::StepsPerEpisode, ::Union{PostEpisodeStage,PostExperimentStage}, agent, env)
+function Base.push!(hook::StepsPerEpisode, ::PostEpisodeStage, agent, env)
     Base.push!(hook.steps, hook.count)
     hook.count = 0
 end
diff --git a/src/ReinforcementLearningCore/src/core/run.jl b/src/ReinforcementLearningCore/src/core/run.jl
index 1e86d732d..1779bd4dc 100644
--- a/src/ReinforcementLearningCore/src/core/run.jl
+++ b/src/ReinforcementLearningCore/src/core/run.jl
@@ -112,10 +112,8 @@ function _run(policy::AbstractPolicy,
             end
         end # end of an episode
 
-        if is_terminated(env)
-            push!(policy, PostEpisodeStage(), env)  # let the policy see the last observation
-            push!(hook, PostEpisodeStage(), policy, env)
-        end
+        push!(policy, PostEpisodeStage(), env)  # let the policy see the last observation
+        push!(hook, PostEpisodeStage(), policy, env)
     end
     push!(policy, PostExperimentStage(), env)
     push!(hook, PostExperimentStage(), policy, env)
diff --git a/src/ReinforcementLearningCore/src/policies/agent/multi_agent.jl b/src/ReinforcementLearningCore/src/policies/agent/multi_agent.jl
index 7acb54834..a81158114 100644
--- a/src/ReinforcementLearningCore/src/policies/agent/multi_agent.jl
+++ b/src/ReinforcementLearningCore/src/policies/agent/multi_agent.jl
@@ -137,10 +137,8 @@ function Base.run(
             end
         end # end of an episode
 
-        if is_terminated(env)
-            push!(multiagent_policy, PostEpisodeStage(), env)  # let the policy see the last observation
-            push!(multiagent_hook, PostEpisodeStage(), multiagent_policy, env)
-        end
+        push!(multiagent_policy, PostEpisodeStage(), env)  # let the policy see the last observation
+        push!(multiagent_hook, PostEpisodeStage(), multiagent_policy, env)
     end
     push!(multiagent_policy, PostExperimentStage(), env)
     push!(multiagent_hook, PostExperimentStage(), multiagent_policy, env)
diff --git a/src/ReinforcementLearningCore/test/core/hooks.jl b/src/ReinforcementLearningCore/test/core/hooks.jl
index 4bde98d0e..c48d050ee 100644
--- a/src/ReinforcementLearningCore/test/core/hooks.jl
+++ b/src/ReinforcementLearningCore/test/core/hooks.jl
@@ -30,6 +30,12 @@ function test_noop!(hook::AbstractHook; stages=[PreActStage(), PostActStage(), P
     end
 end
 
+function test_run!(hook::AbstractHook)
+    hook_ = deepcopy(hook)
+    run(RandomPolicy(), RandomWalk1D(), StopAfterEpisode(10), hook_)
+    return hook_
+end
+
 @testset "TotalRewardPerEpisode" begin
     h_1 = TotalRewardPerEpisode(; is_display_on_exit=true)
     h_2 = TotalRewardPerEpisode(; is_display_on_exit=false)
@@ -42,6 +48,9 @@ end
     policy = RandomPolicy(legal_action_space(env))
 
     for h in (h_1, h_2, h_3, h_4, h_5)
+        h_ = test_run!(h)
+        @test length(h_.rewards) == 10
+
         push!(h, PostActStage(), policy, env)
         @test h.reward == 1
         push!(h, PostEpisodeStage(), policy, env)
@@ -65,6 +74,9 @@ end
     h_5 = TotalBatchRewardPerEpisode(10)
 
     for h in (h_1, h_2, h_3, h_4, h_5)
+        h_ = test_run!(h)
+        @test length(h_.rewards) == 10
+
         push!(h, PostActStage(), policy, env)
         @test h.reward == fill(1, 10)
         push!(h, PostEpisodeStage(), policy, env)
@@ -119,7 +131,7 @@ end
     @test h.steps == [100]
 
     push!(h, PostExperimentStage(), agent, env)
-    @test h.steps == [100, 0]
+    @test h.steps == [100]
 
     test_noop!(h, stages=[PreActStage(), PreEpisodeStage(), PreExperimentStage()])
 end
@@ -133,6 +145,9 @@ end
     h_3 = RewardsPerEpisode{Float16}()
 
     for h in (h_1, h_2, h_3)
+        h_ = test_run!(h)
+        @test length(h_.rewards) == 10
+
         push!(h, PreEpisodeStage(), agent, env)
         @test h.rewards == [[]]