GeezerVison is showing github.com — BY571 - Overview
- Soft-Actor-Critic-and-Extensions: SAC with PER, ERE, Munchausen, D2RL, parallel envs
- CQL: Conservative Q-Learning for offline RL (DQN-CQL & SAC-CQL)
- DQN-Atari-Agents: Modular DDQN, Dueling, Noisy, C51, Rainbow, DRQN
- IQN-and-Extensions: Implicit Quantile Networks with PER, Noisy, N-step, Dueling
- Deep-Reinforcement-Learning-Algorithm-Collection: Reference implementations across deep RL
- Upside-Down-Reinforcement-Learning: Schmidhuber's ⅂ꓤ in PyTorch
- bricksrl: LEGO-based platform for democratizing robotics and RL research · project page
- Autonomous-Robocar: Self-driving RC-car: Raspberry Pi + CNN predicting steering and throttle from camera
- AutomataLeague: Platform for training robots on competitive environments in MuJoCo. Robots race and clear obstacles (parkour), wrestle each other out of a ring (sumo). TorchRL PPO + MuJoCo-Warp, pluggable robots
- SpaceX-Falcon9: Landing a rocket on a drone ship with PPO · write-up
- SpaceX-Mechazilla: Catching a descending rocket with mechanical chopstick arms, Mechazilla style. TorchRL PPO + MuJoCo-Warp · write-up
- pickplace: Franka arm packing items into bowls on a moving conveyor in Isaac Lab. State-based teacher, camera-based students trained with offline RL in TorchRL · write-up
- DistRL-LLM: Distributed RL for LLM fine-tuning across multiple GPUs
- SCoRe: Training language models to self-correct via RL
- sft-kl-lora-trainer:
trl.SFTTrainer with a KL divergence loss between LoRA adapter and base model
- Agent-Tool-RL: Teaching small language models to use tools with RL
- CoT-Decoding: Chain-of-Thought reasoning without prompting
- nanoDiff: Minimal, hackable diffusion language model. nanoGPT for the LLaDA recipe
- artificial-agent-lab: Autonomous research lab: PI and PhD agents run experiments and write papers
- knoten: Research graph that remembers what didn't work. Markdown in git, CLI + SKILL.md so coding agents stop redoing dead experiments
Pinned
Loading
-
PyTorch implementation of Soft-Actor-Critic and Prioritized Experience Replay (PER) + Emphasizing Recent Experience (ERE) + Munchausen RL + D2RL and parallel Environments.
Python
294
35
-
Upside-Down Reinforcement Learning (⅂ꓤ) implementation in PyTorch. Based on the paper published by Jürgen Schmidhuber.
Jupyter Notebook
78
11
-
DQN-Atari-Agents: Modularized & Parallel PyTorch implementation of several DQN Agents, i.a. DDQN, Dueling DQN, Noisy DQN, C51, Rainbow, and DRQN
Jupyter Notebook
122
16
-
PyTorch implementation of the Offline Reinforcement Learning algorithm CQL. Includes the versions DQN-CQL and SAC-CQL for discrete and continuous action spaces.
Python
150
24
-
PyTorch Implementation of Implicit Quantile Networks (IQN) for Distributional Reinforcement Learning with additional extensions like PER, Noisy layer, N-step bootstrapping, Dueling architecture and…
Jupyter Notebook
95
18
-
Collection of Deep Reinforcement Learning Algorithms implemented in PyTorch.
Jupyter Notebook
84
12
Uh oh!
There was an error while loading. Please reload this page.
|
