MDP Playground: Controlling Orthogonal Dimensions of Hardness in Toy Environments

2020-09-28 · Raghu Rajan, Jessica Lizeth Borja Diaz, Suresh Guttikonda, Fabio Ferreira, André Biedenkapp, Frank Hutter

We present MDP Playground, an efficient benchmark for Reinforcement Learning (RL) algorithms with various dimensions of hardness that can be controlled independently to challenge algorithms in different ways and to obtain varying degrees of hardness in generated environments. We consider and allow control over a wide variety of key hardness dimensions, including delayed rewards, rewardable sequences, sparsity of rewards, stochasticity, image representations, irrelevant features, time unit, and action max. While it is very time consuming to run RL algorithms on standard benchmarks, we define a parameterised collection of fast-to-run toy benchmarks in OpenAI Gym by varying these dimensions. Despite their toy nature and low compute requirements, we show that these benchmarks present substantial challenges to current RL algorithms. Furthermore, since we can generate environments with a desired value for each of the dimensions, in addition to having fine-grained control over the environments' hardness, we also have the ground truth available for evaluating algorithms. Finally, we evaluate the kinds of transfer for these dimensions that may be expected from our benchmarks to more complex benchmarks. We believe that MDP Playground is a valuable testbed for researchers designing new, adaptive and intelligent RL algorithms and those wanting to unit test their algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

OpenAI Gym Reinforcement Learning (RL)

MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning

2019-09-17 · Raghu Rajan, Jessica Lizeth Borja Diaz, Suresh Guttikonda, Fabio Ferreira 외

We present MDP Playground, a testbed for Reinforcement Learning (RL) agents with dimensions of hardness that can be controlled independently to challenge agents in different ways and obtain varying degrees of hardness in…

MuJoCo OpenAI Gym reinforcement-learning Reinforcement Learning+1

MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics

2026-03-10 · Neil Janwani, Ellen Novoseller, Vernon J. Lawhern, Maegan Tucker arxiv

Multi-objective reinforcement learning (MORL) is a powerful tool to learn Pareto-optimal policy families across conflicting objectives. However, unlike traditional RL algorithms, existing MORL algorithms do not effective…

Reinforcement Learning

CausalPlayground: Addressing Data-Generation Requirements in Cutting-Edge Causality Research

2024-05-21 · Andreas W M Sauter, Erman Acar, Aske Plaat

Research on causal effects often relies on synthetic data due to the scarcity of real-world datasets with ground-truth effects. Since current data-generating tools do not always meet all requirements for state-of-the-art…

Reinforcement Learning (RL)

Training Versatile Coding Agents in Synthetic Environments

2025-12-13 · Yiqi Zhu, Apurva Gandhi, Graham Neubig arxiv

Prior works on training software engineering agents have explored utilizing existing resources such as issues on GitHub repositories to construct software engineering tasks and corresponding test suites. These approaches…

Hardness in Markov Decision Processes: Theory and Practice

2022-10-24 · Michelangelo Conserva, Paulo Rauber

Meticulously analysing the empirical strengths and weaknesses of reinforcement learning methods in hard (challenging) environments is essential to inspire innovations and assess progress in the field. In tabular reinforc…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)