tinkoff-ai / katakomba
Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)
☆66Updated last year
Related projects ⓘ
Alternatives and complementary repositories for katakomba
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆37Updated last year
- Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC☆52Updated last year
- Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022☆28Updated 2 years ago
- Awesome In-Context RL: A curated list of In-Context Reinforcement Learning☆81Updated this week
- ☆45Updated 7 months ago
- Official implementation for "Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size", NeurIPS 2022, Offline RL Worksho…☆21Updated last year
- Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023☆51Updated last year
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning☆49Updated 3 months ago
- Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"☆27Updated last month
- Challenging Memory-based Deep Reinforcement Learning Agents☆84Updated 2 weeks ago
- ☆16Updated 3 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆105Updated 2 months ago
- ExORL: Exploratory Data for Offline Reinforcement Learning☆104Updated 2 years ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆98Updated 2 years ago
- Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS☆22Updated last year
- Simplifying Model-based RL: Learning Representations, Latent-space Models and Policies with One Objective☆79Updated last year
- ☆28Updated last year
- official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning☆76Updated 3 months ago
- ☆36Updated last year
- Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/☆90Updated 3 years ago
- JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️☆196Updated 3 weeks ago
- ☆53Updated 3 weeks ago
- Benchmarking RL generalization in an interpretable way.☆131Updated 8 months ago
- Synthetic Experience Replay☆71Updated 5 months ago
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆52Updated 7 months ago
- ☆61Updated 2 months ago
- Conservative Q learning in Jax☆50Updated last year
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- Evaluating long-term memory of reinforcement learning algorithms☆132Updated last year