Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TRPO

TRPO

Reported on 84 benchmarks across 3 tasks · 1 paper · 75 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots28 results

Continuous ControlonDouble Inverted Pendulum
Score· 2016-04-22
4412.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonInverted Pendulum (noisy observations)
Score· 2016-04-22
10.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous Controlon2D Walker
Score· 2016-04-22
1353.8
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonMountain Car
Score· 2016-04-22
-61.7
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonCart-Pole Balancing (noisy observations)
Score· 2016-04-22
606.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonHopper
Score· 2016-04-22
1183.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonAcrobot (system identifications)
Score· 2016-04-22
-170.9
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonCart-Pole Balancing (system identifications)
Score· 2016-04-22
980.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonMountain Car (system identifications)
Score· 2016-04-22
-61.6
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonFull Humanoid
Score· 2016-04-22
287
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonAcrobot (limited sensors)
Score· 2016-04-22
-83.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonSimple Humanoid
Score· 2016-04-22
269.7
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonSwimmer
Score· 2016-04-22
96
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonMountain Car (limited sensors)
Score· 2016-04-22
-64.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonAnt + Gathering
Score· 2016-04-22
-0.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonAnt
Score· 2016-04-22
730.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonAcrobot
Score· 2016-04-22
-326
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonMountain Car (noisy observations)
Score· 2016-04-22
-60.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonInverted Pendulum (system identifications)
Score· 2016-04-22
14.1
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonAcrobot (noisy observations)
Score· 2016-04-22
-149.6
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonCart-Pole Balancing (limited sensors)
Score· 2016-04-22
960.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonInverted Pendulum
Score· 2016-04-22
247.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonCart-Pole Balancing
Score· 2016-04-22
4869.8
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonInverted Pendulum (limited sensors)
Score· 2016-04-22
4.5
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonHalf-Cheetah
Score· 2016-04-22
1914
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
Continuous ControlonSwimmer + Maze
Score
0
Continuous ControlonAnt + Maze
Score
0
Continuous ControlonSwimmer + Gathering
Score
0

Methodology28 results

3DonDouble Inverted Pendulum
Score· 2016-04-22
4412.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonInverted Pendulum (noisy observations)
Score· 2016-04-22
10.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3Don2D Walker
Score· 2016-04-22
1353.8
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonMountain Car
Score· 2016-04-22
-61.7
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonCart-Pole Balancing (noisy observations)
Score· 2016-04-22
606.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonHopper
Score· 2016-04-22
1183.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonAcrobot (system identifications)
Score· 2016-04-22
-170.9
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonCart-Pole Balancing (system identifications)
Score· 2016-04-22
980.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonMountain Car (system identifications)
Score· 2016-04-22
-61.6
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonFull Humanoid
Score· 2016-04-22
287
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonAcrobot (limited sensors)
Score· 2016-04-22
-83.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonSimple Humanoid
Score· 2016-04-22
269.7
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonSwimmer
Score· 2016-04-22
96
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonMountain Car (limited sensors)
Score· 2016-04-22
-64.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonAnt + Gathering
Score· 2016-04-22
-0.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonAnt
Score· 2016-04-22
730.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonAcrobot
Score· 2016-04-22
-326
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonMountain Car (noisy observations)
Score· 2016-04-22
-60.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonInverted Pendulum (system identifications)
Score· 2016-04-22
14.1
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonAcrobot (noisy observations)
Score· 2016-04-22
-149.6
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonCart-Pole Balancing (limited sensors)
Score· 2016-04-22
960.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonInverted Pendulum
Score· 2016-04-22
247.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonCart-Pole Balancing
Score· 2016-04-22
4869.8
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonInverted Pendulum (limited sensors)
Score· 2016-04-22
4.5
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonHalf-Cheetah
Score· 2016-04-22
1914
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3DonSwimmer + Maze
Score
0
3DonAnt + Maze
Score
0
3DonSwimmer + Gathering
Score
0

Medical28 results

3D Face ModellingonDouble Inverted Pendulum
Score· 2016-04-22
4412.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonInverted Pendulum (noisy observations)
Score· 2016-04-22
10.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face Modellingon2D Walker
Score· 2016-04-22
1353.8
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonMountain Car
Score· 2016-04-22
-61.7
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonCart-Pole Balancing (noisy observations)
Score· 2016-04-22
606.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonHopper
Score· 2016-04-22
1183.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonAcrobot (system identifications)
Score· 2016-04-22
-170.9
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonCart-Pole Balancing (system identifications)
Score· 2016-04-22
980.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonMountain Car (system identifications)
Score· 2016-04-22
-61.6
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonFull Humanoid
Score· 2016-04-22
287
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonAcrobot (limited sensors)
Score· 2016-04-22
-83.3
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonSimple Humanoid
Score· 2016-04-22
269.7
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonSwimmer
Score· 2016-04-22
96
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonMountain Car (limited sensors)
Score· 2016-04-22
-64.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonAnt + Gathering
Score· 2016-04-22
-0.4
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonAnt
Score· 2016-04-22
730.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonAcrobot
Score· 2016-04-22
-326
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonMountain Car (noisy observations)
Score· 2016-04-22
-60.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonInverted Pendulum (system identifications)
Score· 2016-04-22
14.1
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonAcrobot (noisy observations)
Score· 2016-04-22
-149.6
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonCart-Pole Balancing (limited sensors)
Score· 2016-04-22
960.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonInverted Pendulum
Score· 2016-04-22
247.2
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonCart-Pole Balancing
Score· 2016-04-22
4869.8
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonInverted Pendulum (limited sensors)
Score· 2016-04-22
4.5
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonHalf-Cheetah
Score· 2016-04-22
1914
SOTA
Benchmarking Deep Reinforcement Learning for Continuous Control arXiv:1604.06778
3D Face ModellingonSwimmer + Maze
Score
0
3D Face ModellingonAnt + Maze
Score
0
3D Face ModellingonSwimmer + Gathering
Score
0