[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Updated 2025-10-09 13:40:09 +03:00
OSWorld: A real computer environment for multimodal agents to evaluate open-ended computer tasks
cli
llm
natural-language-processing
artificial-intelligence
language-model
reinforcement-learning
gui
multimodal
agent
benchmark
code-generation
large-action-model
rpa
vlm
Updated 2024-04-29 12:26:03 +03:00
Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We release the trained model on HuggingFace.
machine-learning
nlp
pytorch
large-language-models
finance
chatgpt
reinforcement-learning
technical-analysis
sentiment-analysis
fintech
prompt-engineering
fingpt
robo-advisor
Updated 2024-02-15 23:10:01 +03:00
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
trading
reinforcement-learning
stocks
trading-algorithms
openai-gym
q-learning
trading-environments
dqn
forex
gym-environments
Updated 2023-04-09 18:57:55 +03:00
[NeurIPS 2022] Open source code for reusing prior computational work in RL.
Updated 2022-11-06 21:17:57 +03:00
Repository for portfolio management using Pytorch, SQLAlchemy and XArray. The management is done using the reinforcement learning algorithm "Soft Actor-Critic".
Updated 2022-03-03 23:56:43 +03:00