mit-deep-learning
Tutorials, assignments, and competitions for MIT Deep Learning related courses.
- 10k
- Jupyter Notebook
- MIT
- 3 y ago
Tutorials, assignments, and competitions for MIT Deep Learning related courses.
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
Pytorch code for NeurIPS-20 Paper "Object Goal Navigation using Goal-Oriented Semantic Exploration"
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
Codes accompanying the paper "Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning" (NeurIPS 2021 Spotlight https://arxiv.org/abs/2106.03400)
⚡️ Code and Notes 📝 for Grokking Deep RL and RL: An Introduction by Sutton & Barto(2nd edition, 2018) 🤘
From-scratch reinforcement learning for Balatro — a maskable-PPO agent and an agentic-LLM track, two parity-gated game engines (pure-Python reference + GPU/JAX), and a replay viewer for a hard long-horizon, multiplicative-reward RL problem.
Exploration of deep reinforcement learning and various state-of-the-art techniques to create a turely autonomous agent.