Tags

RL

离线强化学习(一)

离线强化学习简介、policy constraint类方法简介


深度学习与强化学习中的研究与应用(一)

提纲


单智能体强化学习算法

提纲


多智能体强化学习算法

提纲


单智能体强化学习算法

Diversity is All You Need:Learning Skills without a Reward Function


多智能体强化学习算法

Q-value Path Decomposition for Deep Multiagent Reinforcement Learning


多智能体强化学习算法

Multi Type Mean Field Reinforcement Learning


多智能体强化学习算法

Mean Field Multi-Agent Reinforcement Learning


单智能体强化学习算法

Behavior Regularized Offline Reinforcement Learning


离线强化学习

Offline (Batch) Reinforcement Learning的相关工作及应用


单智能体强化学习算法

Data-Efficient Reinforcement Learning with Momentum Predictive Representations


单智能体强化学习算法

CURL:Contrastive Unsupervised Representations for Reinforcement Learning


多智能体强化学习算法

Graph Convolutional Reinforcement Learning


对比自监督学习

对比学习及其在深度学习、强化学习中的进展


单智能体强化学习算法

Unsupervised State Representation Learning in Atari


多智能体强化学习算法

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning


多智能体强化学习算法

From Few to More:Large-scale Dynamic Multiagent Curriculum Learning


多智能体强化学习算法

Action Semantics Network:Considering the Effects of Actions in Multiagent Systems


多智能体强化学习算法

QTRAN:Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning


多智能体强化学习算法

MADDPG:Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments


多智能体强化学习算法

COMA:Counterfactual Multi-Agent Policy Gradients


多智能体强化学习算法

Multiagent cooperation and competition with deep reinforcement learning


多智能体强化学习算法

Malthusian Reinforcement Learning


单智能体强化学习算法

Generalization to New Actions in Reinforcement Learning


多智能体强化学习算法

Emergent Complexity via Multi-Agent Competition


单智能体强化学习算法

Dynamic Weights in Multi-Objective Deep Reinforcement Learning


多智能体强化学习算法

VDN:Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward


多智能体强化学习算法

QMIX:Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning


单智能体强化学习算法

RND:Exploration by random network distillation


单智能体强化学习算法

TD3:Addressing Function Approximation Error in Actor-Critic Methods


单智能体强化学习算法

DPG:Deterministic Policy Gradient Algorithms


单智能体强化学习算法

DDPG:Continuous Control With Deep Reinforcement Learning


多智能体强化学习算法

Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?


单智能体强化学习算法

Rainbow:Combining Improvements in Deep Reinforcement Learning


单智能体强化学习算法

EC:Episodic Curiosity through Reachability


单智能体强化学习算法

ICM:Curiosity-Driven Exploration by Self-Supervised Prediction


强化学习基础知识

动态规划解决MDP的Planning问题


单智能体强化学习算法

Double DQN:Deep Reinforcement Learning with Double Q-learning


单智能体强化学习算法

DQN:Playing Atari with Deep Reinforcement Learning


单智能体强化学习算法

Dueling DQN:Dueling Network Architectures for Deep Reinforcement Learning


单智能体强化学习算法

DRQN:Deep Recurrent Q-Learning for Partially Observable MDPs


强化学习基础知识

MDP


强化学习基础知识

简介


Policy Iteration收敛性及最优性证明


强化学习算法

简介


RL advanced algorithms

单智能体强化学习算法

提纲


多智能体强化学习算法

提纲


单智能体强化学习算法

Diversity is All You Need:Learning Skills without a Reward Function


多智能体强化学习算法

Q-value Path Decomposition for Deep Multiagent Reinforcement Learning


多智能体强化学习算法

Multi Type Mean Field Reinforcement Learning


多智能体强化学习算法

Mean Field Multi-Agent Reinforcement Learning


单智能体强化学习算法

Behavior Regularized Offline Reinforcement Learning


单智能体强化学习算法

Data-Efficient Reinforcement Learning with Momentum Predictive Representations


单智能体强化学习算法

CURL:Contrastive Unsupervised Representations for Reinforcement Learning


多智能体强化学习算法

Graph Convolutional Reinforcement Learning


单智能体强化学习算法

Unsupervised State Representation Learning in Atari


多智能体强化学习算法

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning


多智能体强化学习算法

From Few to More:Large-scale Dynamic Multiagent Curriculum Learning


多智能体强化学习算法

Action Semantics Network:Considering the Effects of Actions in Multiagent Systems


多智能体强化学习算法

QTRAN:Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning


多智能体强化学习算法

MADDPG:Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments


多智能体强化学习算法

COMA:Counterfactual Multi-Agent Policy Gradients


多智能体强化学习算法

Multiagent cooperation and competition with deep reinforcement learning


多智能体强化学习算法

Malthusian Reinforcement Learning


单智能体强化学习算法

Generalization to New Actions in Reinforcement Learning


多智能体强化学习算法

Emergent Complexity via Multi-Agent Competition


单智能体强化学习算法

Dynamic Weights in Multi-Objective Deep Reinforcement Learning


多智能体强化学习算法

VDN:Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward


多智能体强化学习算法

QMIX:Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning


单智能体强化学习算法

RND:Exploration by random network distillation


单智能体强化学习算法

TD3:Addressing Function Approximation Error in Actor-Critic Methods


单智能体强化学习算法

DPG:Deterministic Policy Gradient Algorithms


单智能体强化学习算法

DDPG:Continuous Control With Deep Reinforcement Learning


多智能体强化学习算法

Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?


单智能体强化学习算法

Rainbow:Combining Improvements in Deep Reinforcement Learning


单智能体强化学习算法

EC:Episodic Curiosity through Reachability


单智能体强化学习算法

ICM:Curiosity-Driven Exploration by Self-Supervised Prediction


单智能体强化学习算法

Double DQN:Deep Reinforcement Learning with Double Q-learning


单智能体强化学习算法

DQN:Playing Atari with Deep Reinforcement Learning


单智能体强化学习算法

Dueling DQN:Dueling Network Architectures for Deep Reinforcement Learning


单智能体强化学习算法

DRQN:Deep Recurrent Q-Learning for Partially Observable MDPs


MARL

多智能体强化学习算法

提纲


多智能体强化学习算法

Q-value Path Decomposition for Deep Multiagent Reinforcement Learning


多智能体强化学习算法

Multi Type Mean Field Reinforcement Learning


多智能体强化学习算法

Mean Field Multi-Agent Reinforcement Learning


多智能体强化学习算法

Graph Convolutional Reinforcement Learning


多智能体强化学习算法

Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning


多智能体强化学习算法

From Few to More:Large-scale Dynamic Multiagent Curriculum Learning


多智能体强化学习算法

Action Semantics Network:Considering the Effects of Actions in Multiagent Systems


多智能体强化学习算法

QTRAN:Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning


多智能体强化学习算法

MADDPG:Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments


多智能体强化学习算法

COMA:Counterfactual Multi-Agent Policy Gradients


多智能体强化学习算法

Multiagent cooperation and competition with deep reinforcement learning


多智能体强化学习算法

Malthusian Reinforcement Learning


多智能体强化学习算法

Emergent Complexity via Multi-Agent Competition


多智能体强化学习算法

VDN:Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward


多智能体强化学习算法

QMIX:Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning


多智能体强化学习算法

Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?