About

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Datasets

Latest papers with code

Evaluating Agents without Rewards

21 Dec 2020bfmat/agenteval

Moreover, input entropy and information gain correlate more strongly with human similarity than task reward does, suggesting the use of intrinsic objectives for designing agents that behave similarly to human players.

ATARI GAMES MINECRAFT

2
21 Dec 2020

EvoCraft: A New Challenge for Open-Endedness

8 Dec 2020real-itu/Evocraft-py

In contrast to previous work in Minecraft that focused on learning to play the game, the grand challenge we pose here is to automatically search for increasingly complex artifacts in an open-ended fashion.

MINECRAFT

45
08 Dec 2020

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

29 Sep 2020ml-jku/align-rudder

Align-RUDDER outperforms competitors on complex artificial tasks with delayed reward and few demonstrations.

GENERAL REINFORCEMENT LEARNING MINECRAFT MULTIPLE SEQUENCE ALIGNMENT SAFE EXPLORATION

9
29 Sep 2020

Scaling Imitation Learning in Minecraft

6 Jul 2020amiranas/minerl_imitation_learning

Imitation learning is a powerful family of techniques for learning sensorimotor coordination in immersive environments.

DATA AUGMENTATION IMITATION LEARNING MINECRAFT

10
06 Jul 2020

Forgetful Experience Replay in Hierarchical Reinforcement Learning from Demonstrations

17 Jun 2020cog-isa/forger

There are two main approaches to improving the sample efficiency of reinforcement learning methods - using hierarchical methods and expert demonstrations.

MINECRAFT

5
17 Jun 2020

Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas

1 Jun 2020ylkuo/ltl-zero-shot

We demonstrate a reinforcement learning agent which uses a compositional recurrent neural network that takes as input an LTL formula and determines satisfying actions.

MINECRAFT MULTI-TASK LEARNING

1
01 Jun 2020

Playing Minecraft with Behavioural Cloning

7 May 2020Miffyli/minecraft-bc

MineRL 2019 competition challenged participants to train sample-efficient agents to play Minecraft, by using a dataset of human gameplay and a limit number of steps the environment.

BEHAVIOURAL CLONING MINECRAFT

8
07 May 2020

Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems

27 Apr 2020dlpbc/penn-a

Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning.

META REINFORCEMENT LEARNING MINECRAFT

4
27 Apr 2020

Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft

12 Mar 2020metataro/minerl_agent

Sample inefficiency of deep reinforcement learning methods is a major obstacle for their use in real-world applications.

MINECRAFT

4
12 Mar 2020

Hierarchical Deep Q-Network from Imperfect Demonstrations in Minecraft

18 Dec 2019kimbring2/DQFD_Minecraft

We present Hierarchical Deep Q-Network (HDQfD) that took first place in the MineRL competition.

HIERARCHICAL STRUCTURE MINECRAFT

22
18 Dec 2019