Pinned Loading

1. Awesim Awesim Public

   An Awesome 2D AV Simulator.

   C 1

2. A high-quality, truly single-file im... A high-quality, truly single-file implementation of PPO -- simple to use, transparent, and dependency-light (only torch and gymnasium). Includes a Lagrange penalty-based constrained-MDP solver and supports both continuous and discrete action spaces. Compatible with RNN policies. Designed for clarity, reproducibility, and research-grade performance.

   1

   # -----------------------------------------------------------------------------

   2

   # PPO (Proximal Policy Optimization) — High-Quality Single-File Implementation

   3

   # Author: Abhinav Bhatia

   4

   # Source: https://gist.github.com/bhatiaabhinav/edb07949471c0ae9e71811146cd46311

   5

   #

3. RL3 RL3 Public

   Source code for paper: RL^3: Boosting Meta Reinforcement Learning via RL inside RL^2.

   Julia 8 1

4. Metareasoning.jl Metareasoning.jl Public

   Decision-theoretic metareasoning to control hyperparameter and stopping point of anytime algorithms using deep reinforcement learning.

   Julia 1

5. AnytimeWeightedAStar.jl AnytimeWeightedAStar.jl Public

   Julia Implementation of Anytime Weighted A* (AWA*) and Randomized Weighted A* (RWA*) algorithm

   Julia 3 1

6. RRTStar.jl RRTStar.jl Public

   Julia implementation of RRT* motion planning algorithm.

   Julia 5