StackRating

An Elo-based rating system for Stack Overflow
Home   |   About   |   Stats and Analysis   |   Get a Badge
Rating Stats for

Dennis Soemers

Rating
1516.19 (41,081st)
Reputation
4,937 (33,581st)
Page: 1 2 3 ... 4
Title Δ
Critic Loss for RL Agent 0.00
initialCapacity in ArrayList +0.76
Should the Monte Carlo tree in calculating the previous bestMove be... 0.00
Convolution for state representation 0.00
Java Heap Space Issue with my MCTS Gomoku player 0.00
A very interesting problem with the MiniMax algorithm. What could c... 0.00
Eligibility trace algorithm, the update order 0.00
Deep Q-learning modification 0.00
MCTS *tree* parallelization in Python - possible? 0.00
Stuck in understanding the difference between update usels of TD(0)... +0.48
How does MCTS work with 'precise lines' -0.22
Epsilon Greedy Performing better than UCB for small number of arms 0.00
Tensorflow, OpenAI Gym, Keras-rl performance issue on basic reinfor... 0.00
How to find out values of Policy Iteration? 0.00
What's the rule for training multiple levels of a game using DQ... 0.00
human trace data for evaluation of reinforcement learning agent pla... 0.00
what should the Q matrix dimensions be in an open-like environment... +0.47
Monte Carlo tree search - handling game ending nodes +2.11
Uninformed search: run breadth-first search followed by iterative d... 0.00
Q-learning, how about picking the action that actually gives most r... +0.00
CartPole-v0 stuck at a score of exactly 200 0.00
Q-Learning equation in Deep Q Network +0.48
AI Search Program Doesn’t Output Search Matrix 0.00
A star algorithm: using Heuristic value to act as Tie-breaker where... +0.06
Reinforcement algorithm seems to learn but script is getting stuck... 0.00
My single layer perceptron converges on the OR dataset, but not on... 0.00
Transposition table in Monte Carlo Tree Search algorithm unintended... 0.00
Deep Q Network is not learning +0.45
Why is there no n-step Q-learning algorithm in Sutton's RL book? 0.00
Taking into account information on opponent's likely moves in M... 0.00
Zeta Variable of SARSA(lamda) 0.00
State Space Search: A* and Breadth First Search +1.18
OpenAI-gym how to implement a timer for a certain action in step() 0.00
Tree creation for Alpha-beta pruning 0.00
Error while loading model with RL4J 0.00
Loss decreases but weights don't appear to change during tensor... 0.00
if two features correlate exactly to the target variable, how does... 0.00
Experience Replay is making my agent worse 0.00
OpenAI Integrating custom game into a gym environment 0.00
How can I change baselines code output/replay (PPO) on github? 0.00
Why do we need exploitation in RL(Q-Learning) for convergence? +0.49
Reinforcement Learning function approximation with Neural Networks 0.00
Reinforcement learning with pair of actions 0.00
A* with reopening when heuristics is only admissible but not consis... 0.00
using delay in python makes the code jump.how to solve it? 0.00
Source code Implementation of connected_components(G) function in n... 0.00
Why does defining tf.Session with and without context manager in Te... 0.00
Monte Carlo Tree Search Tic-Tac-Toe -- Poor Agent 0.00
Q Learning Applied To a Two Player Game +0.50
float identity comparison in Python lambda function 0.00