Makrrr/MemComposer
Reinforcement Learning • Updated
Mark
Makrrr
·
AI & ML interests
RL, Agent Memory, RAG
Recent Activity
upvoted a paper about 6 hours ago
MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning updated a collection about 6 hours ago
MemComposer upvoted a paper about 6 hours ago
Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented GenerationOrganizations
Makrrr/qwen3-8B-reasonmed-finetune-extreme
Text Generation • 8B • Updated • 12
Makrrr/qwen2.5-7B-reasonmed-finetune-extreme
Text Generation • 8B • Updated • 16
Makrrr/Qwen3-1.7B-GSM8K-GRPO-verl
Reinforcement Learning • 2B • Updated • 10 • 3
Makrrr/a2c-PandaReachDense-v3
Reinforcement Learning • Updated • 1
Makrrr/Pyramids
Reinforcement Learning • Updated • 40
Makrrr/ppo-SnowballTarget
Reinforcement Learning • Updated • 48
Makrrr/Pixelcopter-PLE-v0
Reinforcement Learning • Updated
Makrrr/Cartpole-v1
Reinforcement Learning • Updated
Makrrr/dqn-SpaceInvadersNoFrameskip-v4
Reinforcement Learning • Updated • 5
Makrrr/QTable-Taxi-V3
Reinforcement Learning • Updated
Makrrr/q-FrozenLake-v1-4x4-noSlippery
Reinforcement Learning • Updated
Makrrr/ppo-Huggy
Reinforcement Learning • Updated • 93
Makrrr/ppo-LunarLander-v2
Reinforcement Learning • Updated • 2