Repro: ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
🎯
Explore experiment logs, traces, and collaborate with an AI agent
👋 Open to Work
Laxmi Tiwari
laxuu
AI & ML interests
Agentic AI, RL, MARL
Recent Activity
updated a Space about 10 hours ago
laxuu/arenarl-icml2026 published a Space about 10 hours ago
laxuu/arenarl-icml2026 reacted to theirpost with 👍 about 1 month ago
Hot take :Wednesday🔥
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
Organizations
updated a
Space about 10 hours ago
published a
Space about 10 hours ago
reacted to their post with 👍🧠🚀❤️🔥 about 1 month ago
Post
207
Hot take :Wednesday🔥
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
posted an update about 1 month ago
Post
207
Hot take :Wednesday🔥
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
For years, AI progress has often looked like:
"Need a smarter model?"
➡️ Add more parameters.
➡️ Add more GPUs.
➡️ Hope your budget survives.
RobotxR1 explores a different idea: what if intelligence comes from experience rather than scale?
Instead of relying solely on massive pretraining, it combines LLMs with reinforcement learning, allowing models to learn through interaction, feedback, and mistakes.
As someone interested in Recurrent RL and autonomous systems, this raises an exciting question:
Are we entering the era where experience becomes more valuable than parameters?
The next breakthrough AI might not be the biggest model.
It might be the one that learns continuously.
📄 Paper: https://arxiv.org/pdf/2505.03238
💻 Code: https://github.com/ForzaETH/LLMxRobot/tree/main
#ReinforcementLearning #LLM #Robotics #AI #smallmodelhackathonhuggingface
liked a
Space about 1 month ago
updated a
Space about 1 month ago
published a
Space about 1 month ago
published a
Space about 2 months ago
updated a
Space about 2 months ago
published 2
Spaces about 2 months ago
published a
model about 1 year ago
updated a
model about 1 year ago
published a
model about 1 year ago
updated 2
models about 1 year ago