karpathy/reinforcejs has 1,495 GitHub stars and 358 forks. GitHot measured 0 stars in 24 hours, +1 in 7 days, and +4 in 15 days. Last checked 2026-11-19 07:17 UTC. Last push 2019-02-18.
計測したスター増加
- 24時間
- 0
- 7日間
- +1
- 15日間
- +4
- 1か月
- 履歴を収集中
期間ごとの純増数です。期間は重複しており、日別の値ではありません。未計測の値は空欄です。スター数は注目度の指標であり、品質の保証ではありません。
概要
Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)
学習README.md
オリジナルREINFORCEjs
REINFORCEjs is a Reinforcement Learning library that implements several common RL algorithms, all with web demos. In particular, the library currently includes:
- Dynamic Programming methods
- (Tabular) Temporal Difference Learning (SARSA/Q-Learning)
- Deep Q-Learning for Q-Learning with function approximation with Neural Networks
- Stochastic/Deterministic Policy Gradients and Actor Critic architectures for dealing with continuous action spaces. (very alpha, likely buggy or at the very least finicky and inconsistent)
See the main webpage for many more details, documentation and demos.
Code Sketch
The library exports two global variables: R, and RL. The former contains various kinds of utilities for building expression graphs (e.g. LSTMs) and performing automatic backpropagation, and is a fork of my other project recurrentjs. The RL object contains the current implementations:
RL.DPAgentfor finite state/action spaces with environment dynamicsRL.TDAgentfor finite state/action spacesRL.DQNAgentfor continuous state features but discrete actions
A typical usage might look something like:
// create an environment object
var env = {};
env.getNumStates = function() { return 8; }
env.getMaxNumActions = function() { return 4; }
// create the DQN agent
var spec = { alpha: 0.01 } // see full options on DQN page
agent = new RL.DQNAgent(env, spec);
setInterval(function(){ // start the learning loop
var action = agent.act(s); // s is an array of length 8
//... execute action in environment and get the reward
agent.learn(reward); // the agent improves its Q,policy,model, etc. reward is a float
}, 0);
The full documentation and demos are on the main webpage.
License
MIT.