Montezuma's Revenge
28 papers with code • 1 benchmarks • 1 datasets
Montezuma's Revenge is an ATARI 2600 Benchmark game that is known to be difficult to perform on for reinforcement learning algorithms. Solutions typically employ algorithms that incentivise environment exploration in different ways.
For the state-of-the art tables, please consult the parent Atari Games task.
( Image credit: Q-map )
Benchmarks
These leaderboards are used to track progress in Montezuma's Revenge
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Arcade Learning Environment
Latest papers
Exploring Unknown States with Action Balance
NeteaseFuxiRL/action-balance-exploration
•
•
In this paper, we focus on improving the effectiveness of finding unknown states and propose action balance exploration, which balances the frequency of selecting each action at a given state and can be treated as an extension of upper confidence bound (UCB) to deep reinforcement learning.
Uncertainty-sensitive Learning and Planning with Ensembles
learningandplanningICLR/learningandplanning
•
•
The former manifests itself through the use of value function, while the latter is powered by a tree search planner.
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives.
Uncertainty - sensitive learning and planning with ensembles
learningandplanningICLR/learningandplanning
•
•
Notably, our method performs well in environments with sparse rewards where standard $TD(1)$ backups fail.
Combining Experience Replay with Exploration by Random Network Distillation
Francesco-Sovrano/Combining--experience-replay--with--exploration-by-random-network-distillation-
•
•
Our work is a simple extension of the paper "Exploration by Random Network Distillation".
Using Natural Language for Reward Shaping in Reinforcement Learning
A common approach to reduce interaction time with the environment is to use reward shaping, which involves carefully designing reward functions that provide the agent intermediate rewards for progress towards the goal.
Go-Explore: a New Approach for Hard-Exploration Problems
Go-Explore can also harness human-provided domain knowledge and, when augmented with it, scores a mean of over 650k points on Montezuma's Revenge.
Exploration by Random Network Distillation
opendilab/DI-engine
•
•
ICLR 2019
In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods.
Empowerment-driven Exploration using Mutual Information Estimation
However, many of the state of the art deep reinforcement learning algorithms, that rely on epsilon-greedy, fail on these environments.
Scaling All-Goals Updates in Reinforcement Learning Using Convolutional Neural Networks
Being able to reach any desired location in the environment can be a valuable asset for an agent.
