Update Acrobot Simulation Leaderboard

data/acrobot/simulation_v2/ar_eapo/README.md

@@ -0,0 +1,4 @@
+# Average-Reward Entropy Advantage Policy Optimisation Controller
+
+This controller uses a policy trained with Average-Reward Entropy Advantage Policy Optmisation. AR-EAPO is an extension of the model-free, maximum entropy reinforcement learning algorithm [EAPO](https://arxiv.org/abs/2407.18143), applied in an average reward setting.
+

data/acrobot/simulation_v2/ar_eapo/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
+1.0,1.394000000000001,8.322843658448338,1.5169970532884,0.008076883429364525,117.96157720290056,0.6326131852346231

data/acrobot/simulation_v2/evolsac/README.md

@@ -0,0 +1,11 @@
+# Evolutionary SAC
+
+## Trajectory Learning, Optimization and Stabilization
+
+This controller uses a trajectory dictated by the policy learned in the following way:
+
+  1. SAC training with loose surrogate reward
+  2. SAC training with stricter surrogate reward
+  3. SNES training with challenge reward + injected noise in the action
+
+The controller uses the final policy network

data/acrobot/simulation_v2/evolsac/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
+1.0,0.9640000000000007,9.260615537277895,2.713043878883556,0.0300476622396909,96.56281902349662,0.5240572289076553

data/acrobot/simulation_v2/mcpilco/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
+1.0,1.446000000000001,19.42529671831582,3.220376833800871,0.09690809960262078,253.58977826055238,0.3164769436997448

leaderboards/acrobot_simulation_performance_leaderboard_v2.csv

@@ -1,4 +1,7 @@
 Controller,Short Controller Description,Swingup Success,Swingup Time [s],Energy [J],Torque Cost[N²m²],Torque Smoothness [Nm],Velocity Cost [m²/s²],RealAI Score,Username,Data
+[mcpilco](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/mcpilco/README.md),Swingup trained with MBRL algorithm MC-PILCO + stabilization with LQR.,1/1,1.45,19.43,3.22,0.097,253.59,0.316,turcato-niccolo,[data](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/mcpilco/sim_swingup.csv) [plot](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/mcpilco/timeseries.png) [video](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/mcpilco/sim_video.gif)
 [TVLQR](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_tvlqr/README.md),Stabilization of iLQR trajectory with time-varying LQR.,1/1,4.05,10.43,1.87,0.016,105.83,0.504,fwiebe,[data](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_tvlqr/sim_swingup.csv) [plot](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_tvlqr/timeseries.png) [video](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_tvlqr/sim_video.gif)
+[AR-EAPO](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ar_eapo/README.md),Policy trained with average reward maximum entropy RL,1/1,1.39,8.32,1.52,0.008,117.96,0.633,rnilva,[data](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ar_eapo/sim_swingup.csv) [plot](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ar_eapo/timeseries.png) [video](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ar_eapo/sim_video.gif)
 [iLQR Riccati Gains](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_riccati_lqr/README.md),Stabilization of iLQR trajectory with Riccati gains. Top stabilization with LQR.,1/1,4.04,10.55,1.98,0.067,106.49,0.396,fwiebe,[data](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_riccati_lqr/sim_swingup.csv) [plot](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_riccati_lqr/timeseries.png) [video](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_riccati_lqr/sim_video.gif)
+[evolsac](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/evolsac/README.md),Evolutionary SAC for both swingup and stabilisation,1/1,0.96,9.26,2.71,0.03,96.56,0.524,AlbertoSinigaglia,[data](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/evolsac/sim_swingup.csv) [plot](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/evolsac/timeseries.png) [video](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/evolsac/sim_video.gif)
 [iLQR MPC stabilization](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_ilqrmpc_lqr/README.md),Online optimization with iterative LQR. Stabilization of iLQR trajectory. Top stabilization with LQR.,1/1,4.86,11.54,2.68,0.096,110.4,0.345,fwiebe,[data](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_ilqrmpc_lqr/sim_swingup.csv) [plot](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_ilqrmpc_lqr/timeseries.png) [video](https://github.com/dfki-ric-underactuated-lab/real_ai_gym_leaderboard/tree/main/data/acrobot/simulation_v2/ilqr_ilqrmpc_lqr/sim_video.gif)