| import { ChevronDown, Loader2 } from "lucide-react"; | |
| import { useEffect, useState } from "react"; | |
| import { useConnectionStatus } from "../../hooks/use-connection-status"; | |
| import { useEmojiAvatar } from "../../utils/avatars"; | |
| import { AsyncImage } from "../common/async-image"; | |
| import { PassComponent } from "../common/pass-component"; | |
| import { Button } from "../primitives/button"; | |
| import { useChains } from "../providers/chain-context"; | |
| import { ConnectButtonRenderer } from "./renderer"; |
| { | |
| "letters": [ | |
| { | |
| "key": "q" | |
| }, | |
| { | |
| "key": "w" | |
| }, | |
| { | |
| "key": "e" |
| def get_layer_output(model, layer, x): | |
| layer_output = None | |
| def layer_output_hook(m, i, o): | |
| layer_output = o.clone() | |
| hook = layer.register_forward_hook(layer_output_hook) | |
| _ = model(x) # call forward hook | |
| hook.remove() | |
| return layer_output |
| x = torch.randn(10) | |
| print(x) | |
| y, ind = torch.sort(x, 0) | |
| print("y", y) | |
| print("ind", ind) | |
| unsorted = y.new(*y.size()) | |
| unsorted.scatter_(0, ind, y) | |
| print("unsorted:", unsorted) | |
| print((x - unsorted).abs().max()) |
| # coding: utf-8 | |
| """ | |
| Seq2Seq (Encoder-Decoder) Model | |
| this model is the basic encoder decoder model without attention mechanism. | |
| author: Keon Kim | |
| """ | |
| import numpy as np | |
| import torch as th | |
| import torch.nn as nn |
| #include <cmath> | |
| #include <cstdio> | |
| #include <vector> | |
| #include <iostream> | |
| #include <algorithm> | |
| #include <stack> | |
| #define WHITE 0 | |
| #define GRAY 1 | |
| #define BLACK 2 | |
| using namespace std; |
| # -*- coding: utf-8 -*- | |
| import random | |
| import gym | |
| import numpy as np | |
| from collections import deque | |
| from keras.models import Sequential | |
| from keras.layers import Dense | |
| from keras.optimizers import RMSprop | |
| EPISODES = 5000 |
| class Fenwick{ | |
| private: | |
| const int maxN = 10000; | |
| public: | |
| int table[maxN]; | |
| int sumQuery(int a, int b){ | |
| return sumQuery(b) - sumQuery(a-1); | |
| } |
Used dueling network architecture with Q-learning, as outlined in this paper:
Dueling Network Architectures for Deep Reinforcement Learning
Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, Nando de Freitas
http://arxiv.org/abs/1511.06581
Command line:
python duel.py CartPole-v0 --gamma 0.995