CORA: Benchmarks, Baselines, And Metrics As A Platform For Continual Reinforcement Learning Agents

Abstract

Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this work, we present CORA, a platform for Continual Reinforcement Learning Agents that provides benchmarks, baselines, and metrics in a single code package. The benchmarks we provide are designed to evaluate different aspects of the continual RL challenge, such as catastrophic forgetting, plasticity, ability to generalize, and sample-efficient learning. Three of the benchmarks utilize video game environments (Atari, Procgen, NetHack). The fourth benchmark, CHORES, consists of four different task sequences in a visually realistic home simulator, drawn from a diverse set of task and scene parameters. To compare continual RL methods on these benchmarks, we prepare three metrics in CORA: Continual Evaluation, Isolated Forgetting, and Zero-Shot Forward Transfer. Finally, CORA includes a set of performant, open-source

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypowers2021cora

Related papers

• Continual World: A Robotic Benchmark For Continual Reinforcement Learning (2021)0.00
• A Continual Offline Reinforcement Learning Benchmark For Navigation Tasks (2025)0.00
• Fightladder: A Benchmark For Competitive Multi-agent Reinforcement Learning (2024)0.00
• CORL: Research-oriented Deep Offline Reinforcement Learning Library (2022)0.00
• OER: Offline Experience Replay For Continual Offline Reinforcement Learning (2023)3.58
• Benchmarl: Benchmarking Multi-agent Reinforcement Learning (2023)5.58
• Population-based Evaluation In Repeated Rock-paper-scissors As A Benchmark For Multiagent Reinforcement Learning (2023)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00