paper-with-me

홈 › Papers

Benchmarking Deep Reinforcement Learning for Continuous Control

2016-04-22 · Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw pixel data and to acquire advanced manipulation skills using raw sensory inputs. However, it has been difficult to quantify progress in the domain of continuous control due to the lack of a commonly adopted benchmark. In this work, we present a benchmark suite of continuous control tasks, including classic tasks like cart-pole swing-up, tasks with very high state and action dimensionality such as 3D humanoid locomotion, tasks with partial observations, and tasks with hierarchical structure. We report novel findings based on the systematic evaluation of a range of implemented reinforcement learning algorithms. Both the benchmark and reference implementations are released at https://github.com/rllab/rllab in order to facilitate experimental reproducibility and to encourage adoption by other researchers.

📄 PDF Abstract BibTeX arXiv:1604.06778

Code (15)

rllab/rllab 공식 구현 tf
Dam930/rllab tf
bstadie/third_person_im tf
cathywu/rllab-multiagent tf
cbfinn/maml_rl tf
jachiam/cpo
openai/rllab tf
rejuvyesh/rllab
richardrl/cartpole-request-for-research pytorch
rll/rllab tf
rlworkgroup/garage tf
russellmendonca/maesn_suite tf
sisl/event-driven-rllab tf
sisl/gail-driver
wyndwarrior/imitation_from_observation tf

Tasks

Action Triplet RecognitionAtari GamesBenchmarkingcontinuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

2022-06-09 · Cong Lu, Philip J. Ball, Tim G. J. Rudner, Jack Parker-Holder 외

Offline reinforcement learning has shown great promise in leveraging large pre-collected datasets for policy learning, allowing agents to forgo often-expensive online data collection. However, offline reinforcement learn…

Benchmarkingcontinuous-controlContinuous ControlOffline RL+3

PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU

2025-01-16 · Trevor McInroe, Samuel Garcin

We present PixelBrax, a set of continuous control tasks with pixel observations. We combine the Brax physics engine with a pure JAX renderer, allowing reinforcement learning (RL) experiments to run end-to-end on the GPU.…

Benchmarkingcontinuous-controlContinuous ControlCPU+2

Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies

2021-11-03 · NeurIPS 2021 12 · Tim Seyde, Igor Gilitschenski, Wilko Schwarting, Bartolomeo Stellato 외

Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space. In this work, we investigate the colloquially known phenomenon that trained agents often pr…

AllBenchmarkingcontinuous-controlContinuous Control+2

FORLORN: A Framework for Comparing Offline Methods and Reinforcement Learning for Optimization of RAN Parameters

2022-09-08 · Vegard Edvardsen, Gard Spreemann, Jeriek Van den Abeele

The growing complexity and capacity demands for mobile networks necessitate innovative techniques for optimizing resource usage. Meanwhile, recent breakthroughs have brought Reinforcement Learning (RL) into the domain of…

Benchmarkingcontinuous-controlContinuous ControlReinforcement Learning (RL)

Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms

2023-11-30 · Xiangyuan Zhang, Weichao Mao, Saviz Mowlavi, Mouhacine Benosman 외

We introduce controlgym, a library of thirty-six industrial control settings, and ten infinite-dimensional partial differential equation (PDE)-based control problems. Integrated within the OpenAI Gym/Gymnasium (Gym) fram…

BenchmarkingOpenAI Gymreinforcement-learningReinforcement Learning+1