paper-with-me

홈 › Papers

CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality

2022-11-12 · Gianluigi Grandesso, Elisa Alboni, Gastone P. Rosati Papini, Patrick M. Wensing, Andrea Del Prete

This paper presents a novel algorithm for the continuous control of dynamical systems that combines Trajectory Optimization (TO) and Reinforcement Learning (RL) in a single framework. The motivations behind this algorithm are the two main limitations of TO and RL when applied to continuous nonlinear systems to minimize a non-convex cost function. Specifically, TO can get stuck in poor local minima when the search is not initialized close to a "good" minimum. On the other hand, when dealing with continuous state and control spaces, the RL training process may be excessively long and strongly dependent on the exploration strategy. Thus, our algorithm learns a "good" control policy via TO-guided RL policy search that, when used as initial guess provider for TO, makes the trajectory optimization process less prone to converge to poor local optima. Our method is validated on several reaching problems featuring non-convex obstacle avoidance with different dynamical systems, including a car model with 6D state, and a 3-joint planar manipulator. Our results show the great capabilities of CACTO in escaping local minima, while being more computationally efficient than the Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) RL algorithms.

📄 PDF Abstract BibTeX arXiv:2211.06625

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Weight Decay 설명 없음
Adam 설명 없음
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},…
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…
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…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
DDPG DDPG, or Deep Deterministic Policy Gradient, is an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action…

Similar Papers 제목 키워드 기반

CACTO-SL: Using Sobolev Learning to improve Continuous Actor-Critic with Trajectory Optimization

2023-12-17 · Elisa Alboni, Gianluigi Grandesso, Gastone Pietro Rosati Papini, Justin Carpentier 외

Trajectory Optimization (TO) and Reinforcement Learning (RL) are powerful and complementary tools to solve optimal control problems. On the one hand, TO can efficiently compute locally-optimal solutions, but it tends to …

Reinforcement Learning (RL)

CACTO-BIC: Scalable Actor-Critic Learning via Biased Sampling and GPU-Accelerated Trajectory Optimization

2026-02-23 · Elisa Alboni, Pietro Noah Crestaz, Elias Fontanari, Andrea Del Prete arxiv

Trajectory Optimization (TO) and Reinforcement Learning (RL) offer complementary strengths for solving optimal control problems. TO efficiently computes locally optimal solutions but can struggle with non-convexity, whil…

Reinforcement Learning

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation

2025-11-20 · Rongxin Cheng, Kai Zhou, Xingda Wei, Siyuan Liu 외 arxiv

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative d…

Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning

2020-11-13 · Jiajun Fan, He Ba, Xian Guo, Jianye Hao

Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods from AlphaGo to Muzero have enjoyed huge success in discrete …

continuous-controlContinuous ControlModel-based Reinforcement Learningreinforcement-learning+2

Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient

2019-11-15 · Kevin Sebastian Luck, Mel Vecerik, Simon Stepputtis, Heni Ben Amor 외

Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the …

continuous-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2