Playing Games
 
Edit

Atari Games

277 papers with code • 64 benchmarks • 6 datasets

The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.

( Image credit: Playing Atari with Deep Reinforcement Learning )

Libraries

Use these libraries to find Atari Games models and implementations
opendilab/DI-engine
12 papers
2,505
chainer/chainerrl
11 papers
1,152
NervanaSystems/coach
7 papers
2,306
chandar-lab/RLHive
7 papers
99
See all 24 libraries.

Datasets

Subtasks

Think Before You Act: Decision Transformers with Internal Working Memory

luciferkonn/dt_mem • 24 May 2023

We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training.

10
24 May 2023
Paper
Code

Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity

xinjinghao/color • 7 May 2023

Meanwhile, the Sparrow simulator utilizes a 2D grid-based world, simplified kinematics, and conversion-free data flow to achieve a lightweight design.

7
07 May 2023
Paper
Code

Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks

google-research/google-research • • 25 Apr 2023

Combined with a suitable off-policy learning rule, the result is a representation learning algorithm that can be understood as extending Mahadevan & Maggioni (2007)'s proto-value functions to deep reinforcement learning -- accordingly, we call the resulting object proto-value networks.

32,745
25 Apr 2023
Paper
Code

Unsupervised Representation Learning in Partially Observable Atari Games

mengli11235/mst_dim • • 13 Mar 2023

Contrastive methods have performed better than generative models in previous state representation learning research.

1
13 Mar 2023
Paper
Code

How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement

liuxhym/adapmen • • 3 Mar 2023

In this paper, we propose a novel active imitation learning framework based on a teacher-student interaction model, in which the teacher's goal is to identify the best teaching behavior and actively affect the student's learning process.

5
03 Mar 2023
Paper
Code

Self-supervised network distillation: an effective approach to exploration in sparse reward environments

michalnand/reinforcement_learning • • 22 Feb 2023

The solution to such a problem may be to equip the agent with an intrinsic motivation that will provide informed exploration during which the agent is likely to also encounter external reward.

2
22 Feb 2023
Paper
Code

Revisiting Bellman Errors for Offline Model Selection

jzitovsky/sbv • • 31 Jan 2023

Offline model selection (OMS), that is, choosing the best policy from a set of many policies given only logged data, is crucial for applying offline RL in real-world settings.

4
31 Jan 2023
Paper
Code

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

khurramjaved96/atari-prediction-benchmark • 20 Jan 2023

We show that by either decomposing the network into independent modules or learning the network in stages, we can make RTRL scale linearly with the number of parameters.

3
20 Jan 2023
Paper
Code

Learning to Perceive in Deep Model-Free Reinforcement Learning

GonQue/gbac • • 10 Jan 2023

We investigate whether a model with these characteristics is capable of achieving similar performance to state-of-the-art model-free RL agents that access the full input observation.

2
10 Jan 2023
Paper
Code

Boosting Object Representation Learning via Motion and Object Continuity

k4ntz/moc • • 16 Nov 2022

Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases.

6
16 Nov 2022
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy