nslyubaykin

BA (Mathematical methods of economic analysis) at HSE

UbisoftMoscow/Russia

Pinned Repositories

cgan_for_edges_to_shoes
Edges to Shoes with cGAN (Pix2Pix)
Language:Jupyter Notebook1 1 00
logos_parser
Parser for Logos from www.brandsoftheworld.com
Language:Python1 1 00
mbrl_multitasking
Model-Based RL Multi-Tasking with ReLAx
Language:Jupyter Notebook2 1 00
music_album_captioning
Music Album Style Image Quoting with Transformers
Language:Jupyter Notebook1 1 00
parallel_ppo
Speeding Up PPO with Parallel Sampling
Language:Jupyter Notebook1 1 10
president_speech
Finetuning GPT2 to answer questions like Vladimir Putin
Language:Jupyter Notebook1 1 00
rainbow_for_2048
Playing 2048 with Rainbow agent
Language:Jupyter Notebook2 1 00
relax
ReLAx - Reinforcement Learning Applications Library
Language:Python15 2 11
relax_mbpo_example
Example MBPO implementation with ReLAx
Language:Jupyter Notebook2 1 00
rnns_for_pomdp
Recurrent Policies for Handling Partially Observable Environments
Language:Jupyter Notebook2 1 20

nslyubaykin's Repositories

nslyubaykin/relax
ReLAx - Reinforcement Learning Applications Library
Language:Python15 2 11
nslyubaykin/mbrl_multitasking
Model-Based RL Multi-Tasking with ReLAx
Language:Jupyter Notebook2 1 00
nslyubaykin/rainbow_for_2048
Playing 2048 with Rainbow agent
Language:Jupyter Notebook2 1 00
nslyubaykin/relax_mbpo_example
Example MBPO implementation with ReLAx
Language:Jupyter Notebook2 1 00
nslyubaykin/rnns_for_pomdp
Recurrent Policies for Handling Partially Observable Environments
Language:Jupyter Notebook2 1 20
nslyubaykin/music_album_captioning
Music Album Style Image Quoting with Transformers
Language:Jupyter Notebook1 1 00
nslyubaykin/parallel_ppo
Speeding Up PPO with Parallel Sampling
Language:Jupyter Notebook1 1 10
nslyubaykin/president_speech
Finetuning GPT2 to answer questions like Vladimir Putin
Language:Jupyter Notebook1 1 00
nslyubaykin/low_res_logos_gan
DC GAN for low resolution logo generation
Language:Jupyter Notebook0 1 00
nslyubaykin/nstep_td3
Multistep TD3 for locomotion
Language:Jupyter Notebook0 1 00
nslyubaykin/ppo_with_dqn_critic
Training PPO with DQN as a critic
Language:Jupyter Notebook1 0
nslyubaykin/prioritized_ddqn
Prioritized DDQN example with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_a2c_example
Example A2C implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_categorical_dqn_example
Example Categorical DQN implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_cem_example
Example CEM implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_ddpg_example
Example DDPG implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_double_dqn_example
Example Double DQN implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_dqn_example
Example DQN implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_dueling_dqn_example
Example Dueling DQN implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_dyna_q_example
Example DYNA-Q implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_frwr_example
Example FRWR (PDDM) implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_noisy_dqn_example
Example Noisy DQN implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_ppo_example
Example PPO implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_rainbow_dqn_example
Example Rainbow DQN implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_random_shooting_example
Example Random Shooting implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_sac_example
Example SAC implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_td3_example
Example TD3 implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_trpo_example
Example TRPO implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/relax_vpg_example
Example VPG implementation with ReLAx
Language:Jupyter Notebook1 0
nslyubaykin/trpo_schedule_kl
Scheduling TRPO's KL Divergence Constraint
Language:Jupyter Notebook1 0