go2sea / C51DQN
A TensorFlow implementation of DeepMind's A Distributional Perspective on Reinforcement Learning.(C51-DQN)
☆56Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for C51DQN
- Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning☆80Updated 6 years ago
- A working implementation of the Categorical DQN (Distributional RL).☆96Updated 6 years ago
- pytorch implementation of Curiosity-driven Exploration by Self-supervised Prediction☆79Updated 5 years ago
- NIPS 2017 Value Prediction Network☆166Updated 6 years ago
- Noisy Networks for Exploration☆185Updated 6 years ago
- ☆161Updated 7 years ago
- Deep Attention Recurrent Q-Network☆116Updated 9 years ago
- reimplementation of the ddpg algorithm using tensorflow☆38Updated 8 years ago
- Accompanying code for "Deep Reinforcement Learning that Matters"☆153Updated 7 years ago
- Modified tensorflow implementation of 'Asynchronous Methods for Deep Reinforcement Learning'☆22Updated 7 years ago
- ☆98Updated 8 years ago
- Implementation of A Distributional Perspective on Reinforcement Learning☆35Updated 7 years ago
- A Tensorflow implementation of Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning☆32Updated 7 years ago
- Implementations of deep RL papers and random experimentation☆177Updated 6 years ago
- TensorFlow implementation of Value Iteration Networks (VIN): Clean, Simple and Modular☆53Updated 7 years ago
- Train an RL agent to play multiple Atari games at once☆71Updated 8 years ago
- A parallel version of Trust Region Policy Optimization☆65Updated 7 years ago
- Implement A3C for Mujoco gym envs☆73Updated 7 years ago
- Reinforcement learning models in ViZDoom environment☆132Updated 2 years ago
- Implimentation of the Model Free Episodic Control paper by Deep Mind : http://arxiv.org/abs/1606.04460☆56Updated 8 years ago
- Exploration Strategies for Deep Reinforcement Learning☆39Updated 6 years ago
- "Continuous Deep Q-Learning with Model-based Acceleration" in TensorFlow☆193Updated 6 years ago
- Advantage async actor-critic Algorithms (A3C) and Progressive Neural Network implemented by tensorflow.☆121Updated 8 years ago
- ☆117Updated 4 years ago
- PyTorch implementation of the Value Iteration Networks (VIN) (NIPS '16 best paper)☆79Updated 7 years ago
- Keras implementation of DQN on ViZDoom environment☆53Updated 8 years ago
- ☆56Updated 6 years ago
- Implementation of "Control of Memory, Active Perception, and Action in Minecraft"☆86Updated 7 years ago