paper-with-me

홈 › Papers

Improving Learning from Demonstrations by Learning from Experience

2021-11-16 · Haofeng Liu, YiWen Chen, Jiayi Tan, Marcelo H Ang Jr

How to make imitation learning more general when demonstrations are relatively limited has been a persistent problem in reinforcement learning (RL). Poor demonstrations lead to narrow and biased date distribution, non-Markovian human expert demonstration makes it difficult for the agent to learn, and over-reliance on sub-optimal trajectories can make it hard for the agent to improve its performance. To solve these problems we propose a new algorithm named TD3fG that can smoothly transition from learning from experts to learning from experience. Our algorithm achieves good performance in the MUJOCO environment with limited and sub-optimal demonstrations. We use behavior cloning to train the network as a reference action generator and utilize it in terms of both loss function and exploration noise. This innovation can help agents extract a priori knowledge from demonstrations while reducing the detrimental effects of the poor Markovian properties of the demonstrations. It has a better performance compared to the BC+ fine-tuning and DDPGfD approach, especially when the demonstrations are relatively limited. We call our method TD3fG meaning TD3 from a generator.

📄 PDF Abstract BibTeX arXiv:2111.08156

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningMuJoCoReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Target Policy Smoothing Target Policy Smoothing is a regularization strategy for the value function in reinforcement learning. Deterministic policies can overfit to narrow peaks in the value…
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…
Adam 설명 없음
Clipped Double Q-learning 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
TD3 TD3 builds on the DDPG algorithm for reinforcement learning, with a couple of modifications aimed at tackling overestimation bias…

Similar Papers 제목 키워드 기반

Self-Imitation Learning from Demonstrations

2022-03-21 · Georgiy Pshikhachev, Dmitry Ivanov, Vladimir Egorov, Aleksei Shpilman

Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated exploration. Learning from Demonstrations (LfD…

Imitation LearningReinforcement Learning (RL)

XPACE: Joint World and Action Modeling from Heterogeneous Experience

2026-09-15 · Jiacheng Wei, Jerry Bai, Xiaoyu Yue, Zidong Wang 외 arxiv

A general-purpose robot needs to draw on diverse experience, choose actions, and anticipate how those actions will change the world. We introduce XPACE, a unified embodied world model that serves as both a world action m…

Video Prediction

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

2019-06-07 · Allan Zhou, Eric Jang, Daniel Kappler, Alex Herzog 외

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising a…

Imitation LearningMeta-LearningMeta Reinforcement LearningReinforcement Learning

Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards

2020-05-01 · ICLR 2020 1 · Allan Zhou, Eric Jang, Daniel Kappler, Alex Herzog 외

Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising a…

Imitation LearningMeta-LearningMeta Reinforcement Learning

Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemble

2022-12-07 · Chao Li

Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement l…

continuous-controlContinuous ControlDeep Reinforcement LearningImitation Learning+4