SourcePulse logoX2,142
HomeBrowse all repos
MishaLaskin avatar

Misha Laskin

Cofounder of Reflection AI

GitHubX

Authored Projects (1)

rad by MishaLaskin

0.2%
411
Research paper implementation for reinforcement learning with augmented data
  • Trains agents using image-based observations and data augmentations.
  • Supports various data augmentations, specified via command-line flags.
  • Implements a RAD agent with SAC (Soft Actor-Critic).
  • Includes logging and TensorBoard visualization for monitoring training progress.
Created 5 years ago
Updated 4 years ago

Starred Projects (15)

ring-flash-attention by zhuzilin

0.3%
869
FlashAttention extension for ring attention
Starred by
willccbb:
pgarbacki:
CodeCreator:
Jiayi-Pan:
+1
Created 1 year ago
Updated 1 week ago

EasyContext by jzhang38

0.1%
746
Recipes for language model context length extrapolation to 1M tokens
Starred by
hiyouga:
jiamings:
pgarbacki:
winglian:
+1
Created 1 year ago
Updated 11 months ago

dolly by databrickslabs

0.0%
11k
Instruction-following LLM trained on the Databricks Machine Learning Platform
Starred by
mateiz:
pgarbacki:
willingc:
JustinLin610:
+14
Created 2 years ago
Updated 2 years ago

chat-langchainjs by sullivan-sean

0%
291
Next.js chat app using LangChain docs as a data source
Created 2 years ago
Updated 5 months ago

zsh_codex by tom-doerr

0.2%
2k
ZSH plugin for AI-powered code completion in the command line
Starred by
omarsar:
parasj:
gravicle:
Created 4 years ago
Updated 6 months ago

emoji-semantic-search by lilianweng

0%
292
Web app for emoji semantic search
Starred by
omarsar:
generall:
Created 3 years ago
Updated 2 years ago

TD3_BC by sfujim

0.3%
373
PyTorch implementation of TD3+BC, an offline RL method
Created 4 years ago
Updated 3 years ago

decision-transformer by kzl

0.3%
3k
RL via sequence modeling research paper
Starred by
aravindsrinivas:
hammer:
chenlin9:
jiamings:
+2
Created 4 years ago
Updated 1 year ago

rad by MishaLaskin

0.2%
411
Research paper implementation for reinforcement learning with augmented data
Created 5 years ago
Updated 4 years ago

whynot by socialfoundations

0%
422
Python sandbox for decision making in dynamics
Starred by
hammer:
mattjj:
Created 6 years ago
Updated 2 years ago

rlpyt by astooke

0%
2k
PyTorch library for deep reinforcement learning research
Starred by
chenlin9:
suquark:
hammer:
jspahrsummers:
+7
Created 6 years ago
Updated 4 years ago

rlkit by rail-berkeley

0.1%
3k
RL algorithm collection implemented in PyTorch
Starred by
aravindsrinivas:
natolambert:
millionintegrals:
jiamings:
+2
Created 7 years ago
Updated 1 year ago

spinningup by openai

0.2%
11k
Educational resource for learning deep reinforcement learning
Starred by
Jiayi-Pan:
pgarbacki:
nirga:
codekansas:
+9
Created 6 years ago
Updated 1 year ago

deep-learning-bitcoin by philipperemy

0%
528
AI model for Bitcoin price pattern exploitation
Created 8 years ago
Updated 7 years ago

evolution-strategies-starter by openai

0.1%
2k
Research paper code for distributed evolution strategies
Starred by
aravindsrinivas:
junxiaosong:
infwinston:
jekbradbury:
+2
Created 8 years ago
Updated 5 years ago
Feedback? Help us improve.