Picture for Weichao Mao

Weichao Mao

Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction

Add code
Apr 12, 2024
Viaarxiv icon

Decision Transformer as a Foundation Model for Partially Observable Continuous Control

Add code
Apr 03, 2024
Viaarxiv icon

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

Add code
Nov 30, 2023
Viaarxiv icon

Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games

Add code
Oct 21, 2021
Viaarxiv icon

Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration

Add code
Oct 12, 2021
Figure 1 for Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration
Figure 2 for Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration
Figure 3 for Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration
Figure 4 for Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration
Viaarxiv icon

Near-Optimal Regret Bounds for Model-Free RL in Non-Stationary Episodic MDPs

Add code
Oct 07, 2020
Figure 1 for Near-Optimal Regret Bounds for Model-Free RL in Non-Stationary Episodic MDPs
Figure 2 for Near-Optimal Regret Bounds for Model-Free RL in Non-Stationary Episodic MDPs
Figure 3 for Near-Optimal Regret Bounds for Model-Free RL in Non-Stationary Episodic MDPs
Viaarxiv icon

POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis

Add code
Jun 08, 2020
Figure 1 for POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis
Figure 2 for POLY-HOOT: Monte-Carlo Planning in Continuous Space MDPs with Non-Asymptotic Analysis
Viaarxiv icon

Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning

Add code
Apr 18, 2020
Figure 1 for Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning
Figure 2 for Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning
Figure 3 for Information State Embedding in Partially Observable Cooperative Multi-Agent Reinforcement Learning
Viaarxiv icon