opendilab/OpenPaL
Building open-ended embodied agent in battle royale FPS game
This project helps AI researchers and game developers create virtual agents that can understand and respond to diverse, arbitrary human instructions in complex environments like first-person shooter games. You provide the agent with language commands, and it learns to perform the necessary actions and acquire new skills, leading to more flexible and human-like AI behavior. This is for researchers building embodied AI agents for interactive simulations or games.
No commits in the last 6 months.
Use this if you need to develop an AI agent that can continuously learn new skills and adapt its decision-making based on open-ended human language commands.
Not ideal if you are looking for a pre-trained agent solution for a fixed set of tasks or a simpler, non-interactive environment.
Stars
38
Forks
1
Language
—
License
—
Category
Last pushed
Feb 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/opendilab/OpenPaL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...