Update Pendubot Simulation Performance Leaderboard

dfki-ric-underactuated-lab · Sep 3, 2024 · f2653be · f2653be
1 parent f398b99
commit f2653be
Show file tree

Hide file tree

Showing 6 changed files with 5,006 additions and 0 deletions.
diff --git a/data/pendubot/simulation_v2/history_sac/README.md b/data/pendubot/simulation_v2/history_sac/README.md
@@ -0,0 +1,2 @@
+# History-based Soft Actor-Critic
+This controller uses a policy trained on an altered version of the model-free, maximum entropy-based Soft Actor-Critic Reinforcement Learning algorithm [Soft Actor-Critic](https://arxiv.org/abs/1801.01290). The model learns latent dynamics from temporal data.
diff --git a/data/pendubot/simulation_v2/history_sac/scores.csv b/data/pendubot/simulation_v2/history_sac/scores.csv
@@ -0,0 +1,2 @@
+Swingup Success,Swingup Time [s],Energy [J],Torque Cost[N²m²],Torque Smoothness [Nm],Velocity Cost [m²/s²],RealAI Score
+1.0,1.1520000000000008,7.673973574502183,2.359531440786147,0.007146586919567306,62.072620040729596,0.6823779743749803
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		# History-based Soft Actor-Critic
		This controller uses a policy trained on an altered version of the model-free, maximum entropy-based Soft Actor-Critic Reinforcement Learning algorithm [Soft Actor-Critic](https://arxiv.org/abs/1801.01290). The model learns latent dynamics from temporal data.
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		Swingup Success,Swingup Time [s],Energy [J],Torque Cost[N²m²],Torque Smoothness [Nm],Velocity Cost [m²/s²],RealAI Score
		1.0,1.1520000000000008,7.673973574502183,2.359531440786147,0.007146586919567306,62.072620040729596,0.6823779743749803