Expired60% confidenceFactExact time
Algorithms supported by decisionrl include online algorithms such as DQN, PPO, SAC, and TRPO, as well as offline RL, model-based methods, multi-agent, and meta-reinforcement learning.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/15/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/13/2026(expired)
Sources
Related Claims
UnverifiedThe underlying layer of decisionrl is a general-purpose RL framework with type annotations and test coverage, supporting mainstream online algorithms such as DQN, PPO, SAC, and TRPO.83% similarUnverifieddecisionrl is an open-source reinforcement learning library developed by developer Denis Drobyshev, specifically targeting operational decision-making problems.65% similarUnverified工具调用层允许模型通过标准化接口如Function Calling操作搜索引擎、代码解释器、日历、邮件等外部系统64% similarUnverified主流本地推理框架包括 llama.cpp、MLX（Apple 为自家芯片优化的机器学习框架）和 Ollama64% similarUnverifiedPrompt Optimizer supports prompt saving and version records, and provides advanced features such as testing, multi-turn conversation, and function calling.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/514226API
curl https://kongchang.com/api/v1/knowledge/claims/514226MCP
get_claim(id=514226)